Citation
Linear rank tests for the nonresponders problem with censored data

Material Information

Title:
Linear rank tests for the nonresponders problem with censored data
Creator:
Pikounis, Vasilis Bill, 1964-
Publication Date:
Language:
English
Physical Description:
xii, 171 leaves : ill. ; 28 cm.

Subjects

Subjects / Keywords:
Censored data ( jstor )
Censorship ( jstor )
Gaussian distributions ( jstor )
Rank tests ( jstor )
Sample size ( jstor )
Significance level ( jstor )
Simulations ( jstor )
Statistical discrepancies ( jstor )
Statistical models ( jstor )
Statistics ( jstor )
Genre:
bibliography ( marcgt )
theses ( marcgt )
non-fiction ( marcgt )

Notes

Thesis:
Thesis (Ph. D.)--University of Florida, 1991.
Bibliography:
Includes bibliographical references (leaves 168-170).
General Note:
Typescript.
General Note:
Vita.
Statement of Responsibility:
by Vasilis Bill Pikounis.

Record Information

Source Institution:
University of Florida
Holding Location:
University of Florida
Rights Management:
Copyright [name of dissertation author]. Permission granted to the University of Florida to digitize, archive and distribute this item for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder.
Resource Identifier:
001717489 ( ALEPH )
AJC9897 ( NOTIS )
25622365 ( OCLC )

Downloads

This item has the following downloads:


Full Text









LINEAR RANK TESTS FOR THE NONRESPONDERS PROBLEM
WITH CENSORED DATA








By

VASILIS BILL PIKOUNIS


A DISSERTATION PRESENTED TO THE GRADUATE SCHOOL
OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT
OF THE REQUIREMENTS FOR THE DEGREE OF
DOCTOR OF PHILOSOPHY

UNIVERSITY OF FLORIDA


1991



























Copyright @ 1991

by

Vasilis Bill Pikounis














To All Those Who Keep Their Dreams Alive















ACKNOWLEDGEMENTS


I make no apologies for my indulgence in the following sentences, since my

completion of this dissertation was helped in so many ways by so many people. First

and foremost, I thank my parents Stamatios and Evangelia for their everlasting love

and their teachings of the tremendous values to be gained from working hard and

earning things in life. The rest of my family and relatives also deserve thanks.

I truly appreciate the wisdom of Dr. P.V. Rao in his guidance of my Ph.D. pro-

gram. I am fortunate for the enthusiasm of statistics shared with a handful of my

fellow students who have become valued colleagues and friends, especially J. Ben

Lang and Carolyn Hansen. I readily acknowledge all the Statistics Department

faculty in the main division that have imparted their vast knowledge of statistics

to me since I was a eager freshman at the University of Florida. I feel very lucky

with the invaluable experience gained in my four years as a data analyst and sta-

tistical consultant in the Division of Biostatistics, due in large part to the superb

professionals that serve as faculty there. In particular, I thank Dr. Michael Con-

Ion and Mr. Phil Padgett for their vision and thankless support that has led to the

workstation computing environment so crucial to this manuscript. In particular, the

wonderful document preparation system ILTEX (Lamport, 1986) and its genesis TEX

(Knuth, 1984) were used to typeset this manuscript; S-plus (Becker, Chambers, and








Wilks, 1989; Statistical Sciences 1990) produced the graphics and simulations, and

Mathematica (Wolfram, 1988) provided numerical integration. Dr. Scott Emerson

deserves thanks for constant help (and never once complaining) in my early days of

trying to learn the workstation environment.

I am grateful for my many longtime friends that have always supported me, and

inspired me to keep going in those times of inevitable valleys.














TABLE OF CONTENTS


page

ACKNOWLEDGEMENTS................................................. iv

LIST OF TABLES ................................. ................. viii

LIST OF FIGURES .................................. ...................... x

ABSTRACT ................ .................................... ........... xi

CHAPTER

1 INTRODUCTION ............................................ 1

1.1 The Nonresponders Problem ............................ 1
1.2 Overview of this Manuscript .................... ...... 4

2 STATISTICAL FORMULATION OF THE NONRESPONDERS
PROBLEM ................................................. 6

2.1 Introduction ......................................... 6
2.2 The Mixture Model .................................... 6
2.3 Literature Review ..................................... 20

3 METHODS FOR CENSORED DATA ........................ 33

3.1 Introduction ....................................... 33
3.2 The Linear Rank Statistic v............................. 34
3.3 Conditions for Asymptotic Properties Under Ho ........ 49
3.4 Asymptotic Normality of v ............................ 60
3.5 Evaluation of Expected Scores ......................... 75
3.6 Properties Under Ha .................................. 81

4 FORMS OF THE TEST STATISTIC ........................... 99

4.1 Introduction ........................................... 99
4.2 Score Functions for Inference about r ................. 100








4.3 Uncensored Data Expected Scores .................... 106
4.4 Censored Data Expected Scores ...................... 110

5 COMPARATIVE STUDIES ................................. 117

5.1 Pitman Asymptotic Relative Efficiencies ............... 117
5.2 Simulation Study .................................... 128
5.3 Real Data Examples ................................. 157

6 SUMMARY AND CONCLUSIONS .......................... 165

REFERENCES ..................................... ...................... 168

BIOGRAPHICAL SKETCH............................................... 171














LIST OF TABLES


Table page

2.1 Pitman ARE for misspecified A, mixed normal distribution ........ 30
2.2 Pitman ARE for location-model vs. mixed-model linear rank test, mixed
normal distribution ................................................ 31
5.1 Pitman ARE for misspecified A under a mixed normal distribution with
exponential and uniform (in parentheses) censoring patterns ....... 121
5.2 Pitman ARE for location-model vs. mixed-model linear rank test, mixed
normal distribution with exponential and uniform (in parentheses)
censoring patterns ................................................ 123
5.3 Pitman ARE for misspecified A under a mixed logistic distribution with
no censoring ....................................................... 125
5.4 Pitman ARE for misspecified A under a mixed logistic distribution with
exponential and uniform (in parentheses) censoring patterns ........ 125
5.5 Pitman ARE for location-model vs. mixed-model linear rank test, mixed
logistic distribution with absence or presence of exponential and uniform
(in parentheses) censoring patterns .............................. 126
5.6 Pitman ARE for misspecified A under a mixed extreme-value
distribution with exponential and uniform (in parentheses) censoring
patterns ................................................... 127
5.7 Pitman ARE for location-model vs. mixed model linear rank test, mixed
extreme-value distribution with absence or presence of exponential and
uniform (in parentheses) censoring patterns ....................... 129
5.8 Empirical powers under a mixed normal distribution and no censoring,
with group sample sizes of 20 ..................................... 140
5.9 Empirical powers under a mixed normal distribution and no censoring,
with group sample sizes of 50 (40) ............................... 142
5.10 Empirical powers under a mixed extreme-value distribution and no
censoring, with group sample sizes of 50 ........................ 144
5.11 Empirical powers under a mixed extreme-value distribution and no
censoring, with group sample sizes of 20 ........................ 147
5.12 Empirical powers under a mixed extreme-value distribution and 10%
exponential and uniform (in parentheses) censoring rates, with group
sample sizes of 50 ............................................. 150









5.13 Empirical powers under a mixed extreme-value distribution and 25%
exponential and uniform (in parentheses) censoring rates, with group
sample sizes of 50 ................................................ 152
5.14 Empirical powers under a mixed normal distribution and 10%
exponential and uniform (in parentheses) censoring rates, with group
sam ple sizes of 20 .................... ........................ ..... 154
5.15 Empirical powers under a mixed normal distribution and 40%
exponential and uniform (in parentheses) censoring rates, with group
sample sizes of 50 .................. ............................. 156
5.16 Change in pain measures from diabetic neuropathy study .......... 158
5.17 Comparison of test statistic values, uncensored data example ...... 159
5.18 Test statistic values and computed p-values,
uncensored data example ........................................ 160
5.19 Survival times in days from Veteran's Administration lung cancer trial,
patients receiving test therapy .................................... 163
5.20 P-values for VA lung cancer censored data example .............. 164















LIST OF FIGURES


Table page

2.1 Graph of extreme-value mixture model; A = 0.5. ................... 13
2.2 Graph of extreme-value mixture model; A = 1.0. ................... 14
2.3 Graph of extreme-value mixture model; A = 2.0. .................. 15
2.4 Graph of extreme-value mixture model; A = 3.0. ................. 16
5.1 1000 random observations from a normal distribution ............. 134
5.2 1000 random observations from an extreme-value distribution ...... 135
5.3 Graph of test statistic behavior, uncensored data example ......... 162















Abstract of Dissertation Presented to the Graduate School
of the University of Florida in Partial Fulfillment of the
Requirements for the Degree of Doctor of Philosophy

LINEAR RANK TESTS FOR THE NONRESPONDERS PROBLEM
WITH CENSORED DATA

By

Vasilis Bill Pikounis

December 1991


Chairman: Pejaver V. Rao
Major Department: Statistics

In a two-sample situation, a two-parameter mixture model is postulated for the

treatment group where a proportion 7r of the subjects are affected favorably by the

treatment, and the remaining proportion of nonresponders behave like the control

patients. The response of interest is subject to random censoring.

A linear rank statistic is developed that has scores that are derived from the

probability of the underlying rank vector arising from data governed by the mixture

model. The technique used to generate the scores is one that emphasizes optimality

properties for values of the parameter 7r in the neighborhood of zero. Writing the

linear rank statistic as a stochastic integral leads to a large sample test procedure.

The performance of the test procedure is compared to standard rank-based tests

in terms of empirical power for a variety of underlying distributions, censoring

xi








patterns, and moderate to large sample sizes. Comparisons via asymptotic relative

efficiency and real data examples are presented as well.

Simulation studies indicate that the mixture model-based test procedures are

more efficient than the standard tests in detecting improvement due to treatment

when the proportion of responders is small and the improvement is substantial.

Because the mixed model test statistic depends on an unknown parameter, the

simulations also provide some guidance in choosing a parameter value that provides

a test that is both sensitive to detect a true treatment effect and is valid in terms

of the chosen significance level.













CHAPTER 1
INTRODUCTION


1.1 The Nonresponders Problem


The "nonresponders" problem may arise in studies designed to evaluate the

efficacy and/or toxicity of new drugs. Such studies generate data from two groups-

the Treatment group consisting of responses to the drug and the Control group

consisting of responses to a placebo. In cases where the drug is designed to combat

one of several different factors that can be the chief cause of the disease, a portion

of the treated subjects will respond like the control subjects. In other words, this

portion of subjects will not respond to the treatment, and the response of interest

can be regarded as an observation that would occur had the subject been a member

of the control group. The subjects are defined to be nonresponders to treatment.

Salsburg (1986) presents an excellent discussion of the nonresponders problem.

He notes that many prospective drug compounds are designed to combat a particular

cause of disease that can be successfully identified and targeted. One example

cited by Salsburg (1986) is an enzyme-inhibitor compound for emphysema. Such

a compound shuts down the activity of a particular proteolytic enzyme that is

known to be a major factor in the presence of the disease. Other patients with

emphysema may not have the enzyme as a primary agent, so that the compound

will consequently not affect the emphysema.








In a similar vein, serum activity of certain enzymes increase when the disease

of hepatitis is present. Medical researchers may try to isolate the enzyme(s) and

investigate whether a lowering of the serum enzyme levels) will result in amelio-

ration of the hepatitis for patients. We may be able only to determine a specific

enzyme as a major risk factor by treating a patient with a compound designed to

specifically act on serum enzyme levels. In cases where the enzyme is the cause of

the disease, the patient will respond, in other cases he/she will not. There is no

external mechanism to determine whether or not a patient is a responder to the

treatment.

Besides enzyme-inhibitors, Salsburg (1986) mentions receptor site agonizers and

hormone-mimickers as prospective compounds to combat conditions such as con-

gestive heart failure and arthritis. Clinical investigations of such compounds will

encounter the same nonresponders problem. Boos and Brownie (1986) mention

the areas of nutritional supplementation and behavioral toxicology where the as-

sumption of the existence of nonresponders is reasonable. The use of antibiotics on

rats infected with the Herpes virus served as an illustration of the nonresponders

phenomenon for Good (1979).

Johnson, Verill, and Moore (1987) reported on a study by Carano and Moore

(1982) in which subject-to-subject variation of complex body mechanisms for deal-

ing with medications resulted in only a subset of subjects reacting to treatment.

Carano and Moore (1982) were interested in studying Sister Chromatid Exchanges

(SCE) as an indicator of carcinogenicity in human smokers. A larger frequency of








high SCE values per cell appeared in many subjects who were smokers, but subject-

to-subject variation was highly prevalent and made it difficult to detect a difference

in SCE distributions for smokers and nonsmokers. The damage in cells was de-

scribed as persistent although only occurring in a small fraction of them. Data for

a similar situation where chemotherapy is a toxic substance that is hypothesized

to increase SCE counts in some cells is given in the Johnson et al. (1987) article.

The counts for a sample of cells from a patient are measured before undergoing the

therapy and again for a second sample taken after administration.

The examples of the nonresponders phenomenon described thus far, particularly

the last one of chemotherapy, involve data that are completely observable. A nat-

ural extension is the scenario in which some of the observations are incomplete, or

censored. This is a feature for responses of the time-to-event nature, such as time-

to-relapse, time-to-death, time-to-recurrence, etc. A subject's observation may only

be known to exceed some value. In medical studies this aspect of censoring produces

what is called survival data.

A clinical trial of cancer patients who receive one of two therapies will involve

data of the time-to-event nature with the feature of censoring. Patients receiving

conventional radiation therapy are considered the "controls," while other patients

receiving a combination of radiation and chemotherapy make up the treatment

group. Conceivably, there may be patients where the chemotherapy has no effect,

and those treated nonresponder patients will have survival times like the control

patients. Clinical trials invariably produce patients surviving at time of analysis,








or perhaps patients "lost to follow-up" by reason of moving away, or death due to

a cause unrelated to treatment. Such patients will have censored times.

Other medical studies attempt to assess the effects of transplanted organs on

survival. The human body's tendency to reject foreign tissue may render the trans-

plantation ineffective, and the individual dies just as if no transplant was received.


1.2 Overview of this Manuscript


The presence of nonresponders in the treatment group is considered in this

dissertation. The potential of censoring on the collected data is taken into account.

Standard techniques as well as newly developed methods for detecting a treatment

effect in the presence of nonresponders and censored data are investigated.

Chapter Two presents statistical formulation of the nonresponder problem. A

model to describe this situation is given. Techniques put forth in the statistical

literature for the nonresponder problem are reviewed. These techniques consider

uncensored data. Chapter Three contains the development of methods for censored

data. Specific forms for these methods under chosen error distributions are given

in Chapter Four. Efficiencies, simulations, and illustrations on real data in order to

compare new methods with the standard methods make up Chapter Five. Summary

and conclusions are in Chapter Six.

The referencing system in this manuscript will follow the convention of number-

ing equations within section. Tables and figures will be numbered within chapter.

Theorems, Corollaries, and Lemmas are counted within section and are numbered






5

independently of one another. For example, the first theorem in Section 2.3 is Theo-

rem 2.3.1, and the first lemma in Section 2.3 is Lemma 2.3.1. The second referenced

equation in that section is (2.3.2).














CHAPTER 2
STATISTICAL FORMULATION OF THE NONRESPONDERS PROBLEM


2.1 Introduction


Statistical models for the nonresponders problem have been consistently written

in terms of cumulative distribution functions in the literature. To accommodate the

prevailing convention in the treatment of censored data, we shall present our models

in terms of survival functions.

In Section 2.2, models suitable for statistical treatment of the nonresponders

problem are formally presented along with notations defined for right-censored data.

A review of statistical research literature pertinent to the modelling for the nonre-

sponders problem is contained in Section 2.3.



2.2 The Mixture Model


Let Xo denote the response variable associated with members in the control

group, and let X1 denote the response variable for those subjects in the treatment

group. Call R the indicator variable which delineates whether or not a treated

subject is a responder, that is,

R 1, if the treated subject is a responder;

0, if the treated subject is a nonresponder.








Then the true proportion of responders in the treated population is given by


r = Pr(R = 1). (2.2.1)


The distribution of Xi, the response for a treated subject, can be represented as

a mixture of two conditional distributions--one the distribution of the response for a

responder subject and the other the distribution of the response for a nonresponder

subject. Let the associated survival functions for the two conditional distributions

be denoted by


FR(x) = Pr(Xi > x I R = 1); FNR(x) = Pr(Xl > x I R = 0),


respectively. Then with 7r as in (2.2.1),


G(x) = Pr(Xi > x)

= Pr(XI > x R = 1)Pr(R = 1) + Pr(Xi > x R = 0) Pr(R = 0)

= 7rFR(x) + (1 rT)FNR(X) (2.2.2)


is the survival function associated with the distribution of X1.

The following assumptions are made throughout the remainder of this disserta-

tion.


Al. The distribution of the measured value for a subject in the control group

is the same as the distribution of a measured value for a nonresponding

subject in the treatment group. That is,


F(x) = Pr(Xo > x) = FNR(X).








A2. The measured value for a responding subject in the treated group is

stochastically larger than the measured value for a treated nonresponder.

That is,

FR(z) > FNR(X) for all x with strict inequality for at least one z.


A3. Both FR and FNR are members of a family of survival functions indexed

by a real parameter A:

F = {F(x : ): 0 < A < +oo}, (2.2.3)

where F(x :A) is continuous with density f(x : A) and is such that

F(x : 0) = FNR(X) = F(x).


Before proceeding further, some comments concerning the three assumptions

are in order. As noted before, Al is a reasonable assumption in many practical

settings. It implies that nonresponding subjects in the treated group behave like

the subjects in the control group. The second assumption, A2, can be interpreted

as implying that the treatment effect, if present, will increase the probability that

the measured value for a responding subject will be larger than a given value. Of

course, the methods that are developed under A2 can be modified to the case where

A2 is replaced by the assumption

A2'. the measured value for a responding subject in the treated group is

stochastically smaller than the measured value for a treated nonrespon-

der. That is,

FR(x) < FNR(X) for all x with strict inequality for at least one x.








Assumption A3, and particularly (2.2.3), when used in the mixture model at

(2.2.2), implies that the survival function for an experimental subject has the form


G(x : r, A) = rF( : A) + (1 7r)F(x),


0 < < 1, O

where F(x) = F(x : 0) is the survival function for the control subjects. The

corresponding density function is given by


g(x : r, A) = rf(x : A) +(l 7r)f(x),


O< r < 1, < A < 00.


The survival functions at (2.2.4) represent a two-parameter family of models for

the two-sample nonresponders problem. In this family, the claim that "there is a

treatment effect" can be interpreted as the claim "a positive proportion of treated

subjects are responders." Thus, a test of the null hypothesis


Ho : No treatment effect,


against the research hypothesis


Ha : There is a treatment effect,


can be performed by testing


Ho : = 0 vs. Ha: R > 0.


(2.2.6)


An examination of the nonresponders model at (2.2.4) shows that the hypotheses

at (2.2.6) are equivalent to the hypotheses


Ho: G(x : 7r, A)= F(x) vs. Ha: G(x: 7r, A) > F(x). (2.2.7)


(2.2.5)








The research hypothesis at (2.2.7) means that X1 is stochastically larger than Xo.

Thus, any two-sample rank test for stochastic ordering, such as the Wilcoxon rank

sum test, will provide a nonparametric test for testing H0 vs. H,. However, since

these tests do not use the specific form of G(x) under Ha, it is natural to search

for tests that are more efficient for testing for treatment effects under the model at

(2.2.4).

For the case where there is no censoring of the data, several authors (Good,

1979; Boos and Brownie, 1986; Johnson et al., 1987; Conover and Salsburg, 1988)

have developed tests of Ho assuming one of the following forms for F(x : A):


(i) Location model: F(x A), -oo < x < oo, A > 0;

(ii) Scale model: F(x/eA), x > 0, A > 0;

(iii) Lehmann model: [F(x)]" -oo < x < oo, A > 0;

(iv) Lehmann model: 1 1 F(x)] -oo < x < oo, A > 0.


Note that F(x : A) is an explicit function of F(x) in the last two cases.

In the context of survival data, the model for scale alternatives appears more

appropriate because survival times are nonnegative random variables whose dis-

tributions are often skewed. However, since the natural logarithm transformation

T(x) = log(x) transforms the scale alternatives to location alternatives, rank-based

tests for the case of a scale model are identical to those for the location-shift model

under the log transformation. Accordingly, in the remainder of this work attention

is confined to location models only.








The models (iii) and (iv) have been explored by Conover and Salsburg (1988).

Their models are expressed in terms of cumulative distribution functions. Indeed, if

we assume our model (iii), then it is straightforward to show that the corresponding

cumulative distribution function is

1 G(x: r, A) = r [1 [F(Z)]] + (1 r)[1 F(x)],

which is their "Model 2." It should also be noted that their parameter a is related

to A through the relationship

a=ea, for a > 1.

Similarly, under model (iv),

1 G(z : r, A) = r [1 F(x)]^ + (1 r) [1 F(x)]

corresponds to the Conover and Salsburg (1988) "Model 1."


A Graphical Example

Consider the location-shift model

G(x : r, A) = rF(x A) + (1 7r)F(x)

for (2.2.4). Values of 7r, the true proportion of responders in the treated population,

will influence the shape of the density in (2.2.5):

g(x : A) = 7rf(x A) + (1 7r)f(x).

The shape of g(x : r, A) will match the shape of the density f(x) for Xo when 7 = 0

or 7r = 1. The degree of modification to the density shape increases as the value of

A tends away from zero and/or the value of Ir tends away from either zero or one.








For the purpose of illustration, let us consider the case where the random variable

X1 IR = 1 has the extreme-value distribution with density


f(x : A) = f(x A) = exp (-(x A) e-(-) .


The series of graphs comprising Figures 2.1-2.4 indicate how the values for r

and A dictate right-tail behavior for the distribution of X1. The location shift

parameter A is labelled Delta in the following graphs. The parameter r is labelled

Pi. When A = 0.5, the shapes of the distributions for X1 (solid line density for

the treatment population) and Xo (dotted line density for the control population)

remain quite similar for the range of values of ir. Differences in the densities only

become apparent for values of 7r > 0.4. In comparison, a distinction between the

densities of Xo and X1 when A = 1 can be seen as early as for the value 7r = 0.2.

The shape for the density associated with X1 "flattens out" at around 7r = 0.5 and

"recovers" as 7r moves away from 0.5. Figures 2.3-2.4 pronounce this phenomenon

more clearly, with suggestion of a bimodal shape.

Figures 2.1-2.4 give us an example of how a location shift parameter A and 7r

interact in terms of their influence on the density shape for the treatment group.


Random Censoring

The presence of censoring in survival data directly affects the information in

samples from the governing model. Several kinds of censoring mechanisms have

been investigated in the statistical literature, each different in its influence on con-

struction of a likelihood for the data. (For example, refer to Kalbfleisch and Prentice






















Extreme-Value, Delta-0.5
PI-02














60I3



PI-O..


I 0 *


P0028















aI a a a a


PI-0.1


















Pi-0.4


Figure 2.1: Graph of extreme-value mixture model; A = 0.5.


- Treatment density g(x : 7, 0.5)

--- Control density f(z)


PI-0.9


















P140.9
I


4 0 a 4 4


P-0.7


-a 4 2 4 I


d





















PI-0.1













* 2 4 *


PI-OA






4 P 0. 4


l\






PI.0.7











4 4


Extreme-Value, Delta-1
Pi602


4 2 4 4 a
PI-05













-t o |


P)-O4













2 0 2 4 I i


P10.3


4 8 2 a a


P10.6



I .












P0.9


!,


Figure 2.2: Graph of extreme-value mixture model; A = 1.0.


- Treatment density g(x : 7, 1.0)

-- Control density f(x)




















Extreme-Value, Delta-2
PI-02


P1.0.4

















P-W7
P6O










P6M


.2 2 2 4 S I


-I I 4 8 1


PI0.5


a 2 4 a a
Fb4~


P.3














-2 I 4 S 8


6!"







i


1 4




Pl6".

P5-o


- I 2


Figure 2.3: Graph of extreme-value mixture model; A = 2.0.


- Treatment density g(x : 7r, 2.0)

--- Control density f(x)




















Pi0.1


P60A


Pi-0.7


- 5 2 4 aI i1a
Rsemme


Extreme-Value, Delta-3
PI-02













-a S 2 4 4 a 'S


















PI-0.5
2 A





















2 a 2 4 10
Pi i0
b: A A

* i i 1




*3 2 1


P 1-0.6
P6.O.6


S a 4 a l


PI.0.9


4 a a 4 $ 10a
I =ere=1


Figure 2.4: Graph of extreme-value mixture model; A = 3.0.


- Treatment density g(x : 7r, 3.0)

--- Control density f(x)








(1980, Ch. 5) for a survey and discussion of the different censoring types and their

appropriateness.)

There are N subjects under study, of which No are in the control group and

V1 are in the treatment group. Let r = 0 for the control group and r = 1 for the

treatment group. Associated with the ith subject in the rth group are two random

variables:


Xri = the potential failure time for the ith subject in group r,

Cr, = the potential censoring time for the ith subject in group r.


For the ith subject in group r, we observe the values of the random variable


X,i = min(Xi, Ci)


and
1,r if Xri = Xi;
0i if X7i = C. .

Thus 6,; takes on the value 1 if the observation for subject i in group r is not

censored and 0 otherwise.

Under the random censorship model, we assume


(1) (Xoi,Co0),..., (XoNo,CoNo), (XI1, C1),..., (X1N, CiN), are mutually in-

dependent pairs.


(2) X,i and C,i are independent and continuous, with survival functions

G(x : 7r, A) and L(x), respectively.


(3) The form of L(x) does not depend upon r or A.







The three assumptions of random censorship implies a noninformative structure

about the censoring mechanism. Most of the results in the statistical literature are

developed under these assumptions. One feature of the noninformative structure is

an opportunity to construct a partial likelihood for the observed data.


Other Notations

When it is necessary to use the random variable associated with the survival

function F(x), the notation of either F or F(X) will be employed in this dissertation.

This convention applies to other random variables as well. A (fixed or random)

function that takes on the values F(x) at the point x may be denoted by either

F(.) or F.

The notation

F,(x) = G(x) L(x) = Pr(Xi > x)

is for the survival function of Xi. Also,

(x) = g( )
G(x)

denotes the hazard function at time x, and


A(x) = jA(s)ds


denotes the cumulative hazard function at time x. The integral of a function such

as A(s) with respect to the variation of s over some interval in R (the real line) will

be denoted as in

0 A(s)ds.








This last integral could also be represented as a Lebesgue-Stieltjes integral with

respect to the total variation of A(x), such as in


fO,x) dA(s).

Estimates from the data of such quantities will be denoted using the "hat" notation;

e.g. F(x) is some reasonable estimate of F(x).

Realizations of Xri are denoted by x,i whether censoring occurs or not. Now sup-

pose that we wish to refer to all the observations irrespective of group membership.

Dropping the subscript r from x,i produces


X1, ... XN


as the observed times for the N subjects in the combined sample. Let ko (kl) denote

the number of distinct uncensored times in the control (treatment) sample, and set

k = ko + ki. Let


0 x(0) < X(1) < X(2) < ... < X(k) < X(k+l) oO


represent the ordered uncensored times in the combined sample. Within the interval

[x(i), x(+l)),i = 0,...,k, suppose that there are mi total censored observations

X(i)1, ..., (i)m,. Define

1, if x(i) corresponds to a treated subject;

0, otherwise.

Thus z(i) is the group membership indicator corresponding to x(i). The censored

values x(i)g, with ( = 1,...,mi, analogously have the covariates z(i)t to indicate








their group memberships. Let

mi
Mi = E z(i
(=1
Then Mi is the number of censoring times belonging to the treatment group in the

interval [X(,), X(;+i)). So mi Mi is the number of censored observations in the

control group that reside in [x(i), x(i+i)). The quantity

k
Ri= (mi + 1)
j=i
will be called "the size of the risk set at time x(i)" and is the number of subjects

whose values are known to be at least x(). The quantities mi, Mi, and Ri do not

have indices in parentheses since they are examples of functions of the x(i). Note

that (i,) does not follow this convention.



2.3 Literature Review


Subrahmanian, Subrahmanian, and Messeri (1975) noted that the use of the

independent sample Student's t-test will suffer from reduced power when the alter-

native hypothesis specifies a mixture of normal distributions. Good (1979) appears

to be the first to introduce the mixture model to account for the existence of non-

responders in the treatment group. To account for the fact that the presence of

nonresponders will decrease the difference between the means of the two groups

and increase the variance of the treatment group, Good (1979) proposed a new

randomization test based on the statistic

X Xo]2
v(0.67) = 0.67 1 I+ + (1 0.67)(N 1)S, (2.3.1)
0+- Vj








where Xo (XI) is the sample mean for the control (treatment) group, and S2 is the

usual sample variance for the treatment group. Notice that the test statistic is a

weighted sum of functions involving the difference in group means and the variance

for the treatment group. The choice of 0.67 by Good (1979) as the weight was made

in hopes of wide applicability of the test over the unknown range of values for ir

and A. Other weights within the interval [0,1] could be used-a weight of 1.0 gives

Fisher's randomization t-test.

The empirical power investigations of Good (1979, Table 1) determined that

the test based on v(0.67) in (2.3.1) performed markedly better over the range of

values 7r E (0, 0.8] than Student's t-test for sample sizes under ten when F(x : A)

represented the standard normal distribution and A = 1,2, or 4. It also beat out

Fisher's randomization t-test over the entire range r E (0, 1] when the underlying

distributions were log-normal. Applications of the test based on v(0.67) in (2.3.1)

showed its evidence of increased "sensitivity" (Good, 1979) relative to Student's t

for real data that exhibit the nonresponders situation. Presumably, the existence of

greater variability in addition to a shift in location for the treatment group responses

made the test based on (2.3.1) better suited than the t-test for rejecting the null

hypothesis of "no treatment effect."

Boos and Brownie (1986) addressed some interesting questions raised by Good's

(1979) paper. The interpretation of a significant p-value was one issue. Boos and

Brownie (1986) emphasized that acceptance of the alternative hypothesis does not

necessarily imply a shift in mean. An increase in the variability could be solely





22

responsible. The graphs in Figure 2.4 indicate how a small r value and a large A

value produces more variability in the treatment group distribution although the

means of the two groups are similar. In addition to correcting the procedure for

implementing a one-sided test with (2.3.1), Boos and Brownie (1986) used Monte

Carlo study results to argue that Student's t-test and the Wilcoxon rank sum test

are at least as powerful as the test based on (2.3.1) when the underlying distributions

were normal or extreme-value and 7r > 0.6. The advantage of (2.3.1) appeared as A

increased and 7r was less than 0.6. Group sample sizes of eight were used. A study

with group sample sizes of twenty did not include (2.3.1); Boos and Brownie (1986)

justified its omission with a statement by Good (1979) of diminished effectiveness

of (2.3.1) as No and N1 grew larger.

The non-technical article by Salsburg (1986), which discussed several applica-

tions of the nonresponder phenomenon, indicates that an interpretation of some

change in the treatment group whether it be primarily due to variability or shift in

mean is useful in preliminary investigations of new clinical compounds. The sample

sizes in such studies are usually small, so that the presence of nonresponders will

decrease power of tests such as Student's t and the Wilcoxon.

The use of Lehmann alternatives in the mixture model for the treatment group

was proposed in a subsequent article authored by Conover and Salsburg (1988). Un-

like the articles of Good (1979) and Boos and Brownie (1986), a formal mechanism

to derive tests sensitive to the alternative hypothesis was used. The mechanism was

Conover's (1973) technique for deriving a locally most powerful rank test (LMPRT)





under more general models than the usual location-shift or scale change settings.

The LMPRT is a linear rank test that is a sum of expected or approximate scores

specifically generated from the given model and assigned to the observations.

Recall that the mixture model (2.2.4) has two parameters, 7r and A. Conover and

Salsburg (1988) took the approach of fixing one of the parameters and deriving the

LMPRT scores for the other. In both cases, the score functions were independent

of 7r. Since both r and A indicate effect due to treatment in the model at (2.2.4),

Conover and Salsburg (1988) were interested in a loss of power that would arise

in using one score function when the other score function was more appropriate.

A comparison of the two score functions in terms of Pitman asymptotic relative

efficiency (ARE) lent creedence to a compromise score function based on a value of

A that maximized the Pitman ARE.

Test statistics based on the scores developed by Conover and Salsburg (1988)

were shown to be asymptotically normal in distribution. For smaller samples,

Conover and Salsburg (1988) suggest the use of the two-sample Student's t-test

computed on the scores. Monte Carlo studies indicated that the empirical signif-

icance levels for the tests were close to the chosen nominal significance level for

sample sizes as few as five in each of the groups when the t-test approximation was

employed. Applying the tests on two examples of real data indicates better perfor-

mance than Student's t, the Wilcoxon, and Good's test based on (2.3.1) in the sense

of calculated p-values. One example, which compares pain values for control and

treated patients undergoing acute painful diabetic neuropathy had sample sizes of








No = N1 = 10. The other example of SGOT liver function values for heart patients

had samples sizes of No = 28 and N1 = 30.

A similar formal approach of ranks was taken by Johnson et al. (1987), where a

location-shift was postulated for F(x : A). Johnson et al. (1987) clearly stated the

testing problem to be the one considered in this manuscript at (2.2.6):


Ho: r = 0 vs. Ha: r >0.


The linear rank tests derived by Johnson et al. (1987) were noted to be based on

score functions that accentuated large responses, which is contrary to the usual

aspect of score functions for rank tests such as the Wilcoxon. The example in

Chapter One of this manuscript that referred to higher SCE counts for patients

receiving chemotherapy served as an illustration of the usefulness of the tests derived

by Johnson et al. (1987). In asymptotic relative efficiencies and Monte Carlo studies,

the derived tests performed better than standard tests such as the Wilcoxon for a

broad range of configurations that reflect the nonresponders problem.

Two underlying forms for F(x : A) were considered-uniform and normal. The

normal distribution with a location shift generated a score function that was de-

pendent on A. The resulting linear rank test could then be used to get an exact

conditional distribution under the null hypothesis. As the sample sizes No and

N1 increase, computations become prohibitive and an asymptotic distribution is

convenient. Also, the score functions may not have tractable expectations so that








approximate scores that are asymptotically equivalent are useful. Results for dealing

with these problems and others are systematically dealt with in the Johnson et

al. (1987) article. The following subsection summarizes their findings.


Properties of Uncensored Data Linear Rank Tests


Under the mixture model at (2.2.4), the score function assigned to z(i) is q(ui),

where

ui = 1 F(x() : 0) = 1 F(x(i)),

and

f(F-l(1-- u) A)
O(u) = f(F u) 1. (2.3.2)
f(F-1(1 u))

The function (2.3.2) will be subsequently designated the "mixed-model" score func-

tion.

The form of the statistic for the LMPRT for testing H0 : r = 0 vs. H. : 7 > 0 is

N
T = z(i) ()(ui)), (2.3.3)
i=1

with the expectation taken over the joint density of the order statistics of a

random sample of size N from a uniform (0,1) distribution. The fact that the ith

order statistic from a uniform (0,1) distribution has a beta distribution with density

N-
N! 1 u -1(1 u1)(N+-)-1 0 < ui < 1,
(i 1)! (N i)!u 0
can be utilized to evaluate T under specific forms for 0 such as when the underlying

distributions F(x A), A > 0 are normal.








Exact significance levels associated with T at (2.3.3) can then be calculated via

the permutation principle. The score function (2.3.2) can also be used with the

approximation

(u.)) (u.) = [ iN+ 1-

to get a statistic
N
T*= Ez(i) (2.3.4)

that is asymptotically equivalent to T at (2.3.3). The approximate scores not only

have easier computational forms but also possess closed-form expressions for most

of the common distributions.

Since computations with all possible permutations can quickly become too in-

tensive as N increases, asymptotic results are employed for assessing significance

levels when N is large. Under mild regularity conditions, standardized versions of

both (2.3.3) and (2.3.4) will be asymptotically normally distributed under the null

hypothesis.


THEOREM 2.3.1 Assume that


(i) 0(u) as defined by (2.3.2) is monotonic.

1
0
(ii) f 2(u)du < oo.

If v is either (2.3.3) or (2.3.4), then under the null hypothesis Ho : r = 0,


ar(v)








where

Var(v) = NN1 (u)du
No + N, J

converges in distribution to a standard normal random variable as min(No, NI) --

oo.


Proof. See Johnson et al. (1987), Theorem 3.1. 0

Behavior of the statistics T at (2.3.3) and T* at (2.3.4) under alternative hy-

potheses has been handled in the context of sequences of local parameter values.

Johnson et al. (1987) provide formal details in the appendix of their article. The

distributions of T and T* under sequences of local alternative hypotheses are asymp-

totically normal and can be used to obtain efficiency expressions. As mentioned

before in review of the Conover and Salsburg (1988) article, the Pitman ARE can

be used to help determine a value for A in order to conduct the test. Let a > 0 be

some constant. Under a limiting sequence of local alternatives

a
r* = 7, min(No, Ni) -- oo, (2.3.5)


the Pitman ARE can be computed to explore loss of efficiency for a particular LM-

PRT due to inaccurate specifications such as the value of A. Since the test statistics

depend on A, a choice of some value to substitute for a unknown parameter is an

important issue. This section introduces some evidence of the problem. Further

study in hopes of finding adequate solutions is discussed in later chapters, after the

censored data case is considered.







Suppose ch(u) denotes the chosen score function to be used, while Ot(u) denotes

the score function which contains the true value of A. That is, let


/ch (u) = -1
'Oh(u) = f(F-1(1 u) Ah) 1,
f(F-'(1 u))

and

Sf(F-(l u) At)
f (F-1(1 u)) -

where Ach is the chosen value of A, and At is the true value of A.


THEOREM 2.3.2 Under the conditions of Theorem 2.3.1 and (2.3.5), the Pitman

ARE of the test statistic v based on Och(u) relative to #t(u) is

J [ch(u)t(u)du
eff(Ah, At) )= 10
f (udu J(u)du

Proof. See Johnson et. al (1987), Theorem 3.2. 0

The computation of a Pitman ARE may be simplified with the next result.

LEMMA 2.3.1 For the mixed-model uncensored score function 0(u),
1
/ (u)du = 0,
0
or equivalently,

/f(F-1(1-u A)du = 1
f (F-(1 u))

Proof. The integration substitution x = F-1(1 u) produces
1 00f :A
I(u)du = f ) f(x)dx 1
0 --oo
= 1-1=0.0








Cross product terms that arise when components of the Pitman ARE are ex-

panded out will involve the same type of integral as given in Lemma 2.3.1, thereby

leading to simplified evaluations.


An Example

Theorem 2.3.2 can be used to evaluate a (Pitman) ARE for some particular

distributions when the unknown parameter is misspecified. Any mention of ARE

in this dissertation implicitly refers to Pitman asymptotic relative efficiency.

The ARE expression in the theorem can also be employed to compare the mixed-

model scores test with the linear rank test derived under the usual location-shift

model. Score functions such as those for the Wilcoxon and log-rank take the place

of Och(u). The mixed-model scores are substituted into 4t(u).

An illustration using the normal distribution for F(x A) is now presented.

Recall that Johnson et al. (1987) chose the normal distribution to derive a mixed-

model score function. First we note that because 0(u) does not have a closed-form,

the expected score corresponding to x(i) must be numerically evaluated. A general

expression for the expected score is

CN! 1
= (i -1)! (N i)! (i)(Ui)i1 u)


Now refer to Theorem 2.3.1. Since all components of the first derivative

AeF-(1-u)
( f(F-1(1- u))

exceed 0, condition (i) holds. Also, condition (ii) holds for any A > 0, since by









Table 2.1: Pitman ARE for misspecified A, mixed normal distribution


At

Ach 0.5 1.0 1.5 2.0 2.5 3.0

0.5 1.00 .860 .518 .194 .042 .009

1.0 .860 1.00 .831 .443 .141 .026

1.5 .518 .831 1.00 .801 .393 .115

2.0 .194 .443 .801 1.00 .784 .732

2.5 .042 .141 .393 .784 1.00 .780

3.0 .009 .026 .115 .372 .780 1.00


straightforward integration,

1
J0(u)du = e2 -1.
o

This provides the asymptotic properties of v when the underlying survival distribu-

tion is mixed normal.

For studying misspecification of A, Table 2.1 is an extension of Table 3 in John-

son et. al (1987). Again by straightforward integration, the algebraic form of the

ARE for misspecified A is

Le-1 +A2-At+&,h)2) 2]
ef[e A ] [ei i]


Now we turn to model misspecification. Table 2.2 is an extension of Table 3 in

Johnson et al. (1987). In comparison to the normal scores tests of Fisher & Yates









Table 2.2: Pitman ARE for location-model vs. mixed-model linear rank test,
mixed normal distribution


A for mixed-model score

0.5 1.0 1.5 2.0 2.5 3.0

0.880 0.582 0.265 0.075 0.012 0.001




(1963) and van der Waerden (1953), Table 2.2 indicates that the mixed-model scores

have a distinct advantage for A > 1.0. This was pointed out in Table 1 of Johnson et

al. (1987). The SCE data example in Johnson et al. (1987) makes the only mention

by the authors on a choice for A in practice, which was A = 1. A look at the results

of their Monte Carlo study suggests that the mixed-model test when the underlying

distributions are normal has better power than the standard location-shift normal

scores test or the Wilcoxon test. This was particularly true for true values of A = 2

or A = 3 and samples sizes of 10, 20, and 40 per group. Choosing A = 0.5 or 1.0 or

1.5 or 2.0 to calculate the test statistic gave very similar empirical powers in most

cases.


Discussion


The articles that we have reviewed in the literature have dealt with rank-based

methods for the nonresponders problem with complete observations. A believed

advantage of deriving scores based on ranks is their robustness to departures from

the assumed underlying distributions F(z : A). Additionally, the invariance to








monotone transformations is a worthwhile feature. The property of locally most

powerful rank tests is appealing as well, since it is usually the case that such rank

tests do well for nonlocal alternatives. Extensions of these procedures constitute

the thrust of the remainder of this manuscript. One topic is the use of other dis-

tributional forms for F(x : A) other than the normal. The main interest, however,

is to develop scores and linear rank tests that allow for the potential of censored

observations. One way to derive such scores is from the so-called rank likelihood.

Once such scores are generated, distributional properties need to be considered for

inferential purposes.

The issue of how to choose A to conduct the test in practice demands more

attention than what has been given in the literature. To this end, more study is

warranted on the behavior of the tests as different values of A are chosen.













CHAPTER 3
METHODS FOR CENSORED DATA


3.1 Introduction


Investigation of the properties associated with a linear rank test statistic for

censored data requires a different approach than that for the case where no censoring

occurs. A useful technique in similar and common inference situations is to cast the

test statistic as a stochastic integral. This enables the use of the theory of counting

processes and martingales to derive asymptotic properties. Aalen (1978) and Gill

(1980) were responsible for much of the foundational work of this approach. Their

findings have been applied numerous times by researchers in the area of censored

data linear rank statistics.

In Section Two of this chapter, a rank-based likelihood is derived for censored

data under the mixture model (2.2.4). The likelihood is used to determine the form

of the linear rank statistic, v, for testing Ho : 7 = 0. The equivalent expression

of v as a stochastic integral is also derived. Section Three explores asymptotic

equivalence of linear rank statistics when v employs certain scores that approximate

the expected scores. Also introduced are some preliminary results that are needed

to establish the asymptotic normality of a properly standardized version of v. The

asymptotic properties under the null hypothesis make up the content of Section

Four. The results and discussion in Section Five focus upon score expressions for

33

















I


v that may be useful in practical applications. Properties of v under alternative
hypotheses are presented in Section Six.
3.2 The Linear Rank Test Statistic v
Rank Likelihood for the Data
Kalbfleisch and Prentice (1973) defined a censored data rank statistic as the set
of all rank vectors of uncensored survival times that can give rise to the observed
ranks of the data. The probability of the observed censored data rank statistic,
P(r), can be calculated by summing up the probabilities of all possible underlying
rank vectors given the censoring pattern of the data. All possible rankings of the
sample that might be observed if we could measure the actual survival times for
each subject are added together to get P(r).
The Kalbfleisch and Prentice (1973) formulation does not take into account the
order of the censored observations inside an interval defined by two adjacent ordered
uncensored values. Sacrifice of this ordering information should be negligible in the
relative presence of a decent number of uncensored observations (Prentice, 1978).
Recall the mixture model at (2.2.4) as
G(x : r, A) = G(x) = rF(x : A) + (1 r)F(x),
with A > 0 and 7r E [0, 1]. A representation of P(r) for data sampled under model
(2.2.4) and the random censorship structure is










k
P(r) = /. J f(X,)1)-'l [Wf(7() : A) + (1 7r)f(x() : 0)]6)
X(I) x [F(x() : 0)]m"-M'[rF((,) : A) + (1 r)F(x() : 0)]M dx(). (3.2.1)


Because the censoring distributions are assumed to not depend on Ir and A, the

censoring distributions are not included in the likelihood expression at (3.2.1). This

"rank likelihood" allows generation of scores in linear rank statistics for various

choices of F(x : A), A > 0. A mechanism for deriving linear rank tests from

P(r) parallels the technique for constructing locally most powerful rank tests with

uncensored data for the usual types of alternatives-location, scale, and regression

(e.g. Hajek and Sidik, 1967).


A General Form

There are three conditions of Hajek and Sidak (1967, p. 70) that are sufficient for

deriving locally most powerful rank tests. A version of these conditions appropriate

for the purposes of this dissertation is:


(i) For some e > 0, the survival function G(x : r, A) and the density

g(x : 7r, A) are continuous in r : :r E [0, e] for every x.


(ii) The limits

dG(x: r, A) .iG(x : 7, A) G( : 0, A) l G(x : r,A)-F(x)
dir r=O -.,o 7 .-O -7


and











dg(x : r,A) g(X :r,A)--g(x :O,A) im g(x :r, A) f(x)
=li : lim g (m
dTr ,=O r--0 7" r-o

exist for every x.


(iii)

( : 7d da < oo for every A
0 dir
-00
and

SdG(x:rA) f() d < oo for every A.
dir F(x)
-00

We now introduce the general form of v in the following theorem.


THEOREM 3.2.1 Consider the two-sample data situation given by (2.2.4):


G(x) = G(x : r, A) = 7rF(x : A) + (1 r)F(x).


Suppose the support of F(x) is contained within that of F(x : A), and there exists

a positive constant B < oo such that


SF(x) f() dx = B. (3.2.2)
-oo

Then a rank test for testing


Ho: = 0 vs. H,: > 0


in the model (2.2.4) can be based on the statistic

k
v = z(zci + MC) (3.2.3)
i=1








where

k
ci = ..]. (u,) {Rj(1 ui)m du,}, (3.2.4)
l<
and


C,= /.. (u) {R(1 u)m dua}, (3.2.5)
u <... with

= f(F-1(1 u): A)
f(F-1(1 u))

and

Iu) F(F-1(1 u) : A) F(F-(1 u): A)
F(F-1(1 u)) (1 u)

Proof. Following Johnson et al. (1987, p. 654), a proof of Theorem 3.2.1 can be

given by verifying the three conditions on page 35 of this manuscript. For some

e > 0, (i) the survival function G(x : r, A) = (1 r)F(x) + rF(x : A) and the

density g(x : 7r,A) = (1 7r)f(x) + f(x : A) will be continuous in r : r E [0,e]

for every x. The one-sided nature of the interval [0, e] does not affect the validity of

Hajek and Sidak's conditions according to the argument of Johnson et al. (1987).

Next, (ii) the limits

lim G(: 7r, A) G(x: 0, A) = im G(x) F(x)
r-O 7 r-*O r7

= lim (1 r)F(x) + rF(: A) F(z)

= F( : A) F(z)


and

g( : r,A) g(x: 0,A) limg() f()
lim = im
7r-O r-.O





lim (1 r)f(x) + Irf(x: A) f(x)
r-+O 7

= f(x: A) f(x)

exist for every x; and (iii)
+00
SJIG(x : -r,A)- G(: 0,A)(x : A
S G(x : 0, A): OA)(dx
-00
+ F( : A) F(x)j
=- F(x) f(x)dx
-00
+00 +00
< F(x:A)f( + f F (x))dx
-00 -00
+00
J F(x : A)
f(x) dx + 1
-00
=B+1< oo

when the supposition at (3.2.2) holds, and
+00
I g(x: r,A) -g(x : O,A)dx
-00
+00
= Jf (fx:A)-f(x)\dx
-00
+00 +00
f If(x: A)( dx+ If(x)ldx
-00 -00
= 1+1= 2 < o.


To derive the linear rank test statistic based on (3.2.1), refer to Prentice (1978) as

a basis for the following representations. Conditions (i)-(iii) being satisfied ensures

that differentiation and integration interchange is permissible. The rank probability

(3.2.1) can be expressed as


P(r)= ... (2-dx(<),
X(1)






where Pi represents the contribution to the likelihood of failure time xz( and the

censored observations x(o)i,... (m, contained in the interval [x(),x(i+l)):

Pi = f(x(i))-z' [rf (x() : A) + (1 7r)f(x(i : 0)](')

x [F((,) : O)]m,-M'[7F(x(.) : A) + (1 r)F(() : 0)]M. dx().

Then

Slog P(r) P(r) /P()


P(r) ) "'"II f1dx(
p(r) [J ... Ik Pax(]
4 I 1 dX*]
(r) / i= /

[I '" log Pj) Pi dx(o ]

P(r)= ilog PI Pidx(i) (3.2.6)
1r) [=[1 i=1

Evaluation of the right-hand side of (3.2.6) at the null value 7r = 0 provides the

form of the linear rank statistic given by (3.2.3). To illustrate this, first note that

P(r) = II f (x())F(x(,))m' dx(),
r=O X(i)<...
which can be directly integrated (Prentice, 1978) to arrive at the result

P(r) = H -. (3.2.7)
r=o i=1
Next, observe that

a log Pi
i=1 r=O
= -{(1 z(j))log f(x()) + (mi Mi)logF(x(1))
i=1







+z() log[7rf(x() : A) + (1 r)f (x())]

+ Milog[7rF(x(:) A) + (1 7r)F(x())]}
Ir o
= (x() A) + ( r)f(x(i))]
= [ z,)[rf(x(3) A) + (1 :)f(xy)]

+ F((i : A) F(zx())
[rF(x() : A) + (1 r)F(x(.))] --o
k f f(x() : A) f(x(,)) F(x() : A) F(x())
f(xzi) F(x() f
= z f( (i) :) 1 + M [ F(x()) -: (3.2.8)

Putting (3.2.6)-(3.2.8) together and then using the substitution uj = 1 F(x(j))

yields the linear rank test statistic given by (3.2.3) with scores (3.2.4) and (3.2.5).

0

The score functions (3.2.3) were reported in Johnson et al. (1987) for the situa-

tion of uncensored data and location-shift form for F(x : A). Conover and Salsburg

(1988) derived specific scores corresponding to a Lehmann-alternative choice of

F(x : A). The next corollary summarizes the notion that the resulting linear rank

statistics provide locally most powerful rank tests in the uncensored data case.

COROLLARY 3.2.1 Under the conditions of Theorem 3.2.1, suppose that there are

no censored observations. The locally most powerful rank test (LMPRT) is given by

the form (3.2.3) with the scores (3.2.4).

Proof. Set Mi = 0 in (3.2.3). This gives (2.3.3), the LMPRT as discussed in Section

2.3. o

The following lemma contains a sufficient condition for (3.2.2) in Theorem 3.2.1

when F(x : A) = F(x A).





41

LEMMA 3.2.1 Let B be a positive constant such that B < oo, and let (.-) be defined

as in (2.3.2) or (3.2.4). If F(x : A) = F(x A), then



2(u)du = /(F-[(1 u) A)du < B/2
0 0
implies that
oo F(X-A)
I F (x)) f(x)dx < B.

Proof. Make the substitution u = 1 F(x) and integrate-by-parts to show

7 F(x A) F(F-'(1 u) A)d
I F(x) 1 u
-oo 0
= [-log(1 u)F(F-(1 u) )

/ ^f (F-'(1 u) A)
log( ) f(F (1 u) A)du. (3.2.9)
0 f(F-1(1 u))

Now the first term on the right-hand side of (3.2.9) contains the form oo 0 when

evaluated at u = 1 and thus requires some extra handling to show that its value is

zero. Let I[A] denote the indicator function which takes on the value 1 when the

event A occurs and 0 otherwise. Let X be the random variable with the survival

function F. The substitution x = F-l(1 u) leads to


lim log(1 u)F(F-(1 u) A)] = lim log(F(x))F(x A)
u-"*1 X"-oo
= lim- log(F(x))E[x>,_a]

< lim E[-log(F(X))]r[x>z-a]

(for log(F) is monotone increasing)

= lim [- log(F(X))]
X--00







limn [- log(F(X))]ZTx<;_-Al

= 1-1=0


by the Monotone Convergence Theorem and the fact that
1
S[- log(F(X))] = log(1 u)du = 1.
0

The second term on the right-hand side of (3.2.9) is also finite since
2
/ g f(F-i(1 u) A)) 2
log(1 f(F1(--u)- du


<([log(,1- u)]2 du) ([f (F-1(1 u) A)

< 2. (B/2) < oo


by the Cauchy-Schwarz inequality and by the sufficient condition of the lemma. 0

The condition in Lemma 3.2.1 is closely related to large-sample properties for

the linear rank statistic v. As can be seen from Theorem 2.3.1, it is the primary

component of an expression for the asymptotic variance of v with uncensored data,

which is required to be finite.


Alternate Summation Form for v

It has been common and convenient in the literature to display linear rank statis-

tics for testing equality of survival distributions in the form of a sum of weighted

differences between the number of observed deaths and the number of conditionally

"expected" deaths. Conditioning is done on the prior failure and censoring history

observed. Tarone and Ware (1977) and Prentice and Marek (1979) formally discuss








this form for some of the more well-known test statistics. Authors such as Harring-

ton and Fleming (1982) consider whole classes of statistics that are distinguished

by the choice of the weights on the differences.

Recall the definition R, of the size of the risk set in Section 2.2. Let Rli be

the number of treated subjects in the risk set at failure time x(i) and Roi be the

corresponding number in the control group. Note that Roi + Rui = Ri. The present

goal is to represent v (defined in (3.2.3)-(3.2.5)) in the following form:


E w z(O) (3.2.10)

where

wi = c C (3.2.11)

is the weight function associated with the failure time x(i).

A sufficient condition for v to have the form at (3.2.10) and (3.2.11) is that the

scores ci and C, satisfy


RCi-C = ci + (Ri 1)C; i = 1,...,k, (3.2.12)


where Co = 0. The condition at (3.2.12) was first derived by Prentice and Marek

(1979), who used it to represent the log-rank (Mantel 1966; Cox 1972), Gehan

(1965), and Peto & Peto (1972) statistics in the form (3.2.10). Since v can be

rewritten (Prentice and Marek, 1979) as the sum of the form (3.2.10) and a quantity:


v = wi (z() -R + I z(i) (ci Ci Ri(Ci-I Ci)), (3.2.13)
1=1 i =1

where the second term on the right-hand side of (3.2.13) equals zero when (3.2.12)







holds, we concentrate on showing that the relation (3.2.12) indeed holds for the

mixed-model scores c, and Ci.

In full notation, (3.2.12) is expressed as

F(F-'(1 u-) : A) k
F1 Rj(1 uj)m' dui
u <. ff (F-1(1 u) : A) k
J..J R(F-'(l1 ui)) -1 k Rj(1 uj)"i dui
ul <. +((I F(F-l(1 u,) : A)
< ui<'- k
x iI Rj(1 uj)j' duj.
j=1

Expanding the above full version of (3.2.12) yields


/../ (F(F- t(1 ~i-) :F R I R(1 u,) du,
ul <... ( f (F-'(1 u,) : A) k
J (f (F-1(1 u1)) j R '(1 us)'m du,
Ul<... A 1) F(F-1(1 uj) RA) +
U1<... k
x J< Rj(1 uj)m, duj.
j=1

Cancelling common terms on both sides and simplifying gives for (3.2.12):

F(F-1(1 unj-) : A) k
-- i F(F-(1- ui) Rj(1 -uj)' du
u<... f (I / f(F-'(1 u) :A)\ )
=( 1f(F1I(l )) } I R,(1 u,)m' duj
f(F-1(1 ui)) ,.=l
) j F(F-1(1 u) : A)
+ < F(F-1(1 u,))
k
x iI R,(1 uj)' duj. (3.2.14)
j=1








Assume that Ri > 1. We adapt a technique employed by Mehrotra, Michalek,

and Mihalko (1982). Starting with the second term on the right-hand side of

(3.2.14), first integrate out ui+1,... k to get

(R 1)1 1 F(F-'(1 u) : A)( uRi
JuiI 0 a F(F-1(1 uj))
i-1
x I {R(1 uj)'m' du,}du,
j=1

=(R-)- J1) n{R(1l-uj)"' du,}
U-_2 j=

x F(F- R(1 ui)R-.du. (3.2.15)
Ju,_- (1 ui)

Next, apply the integration-by-parts technique to the integral over u,. Let


U = F(F-(1 ui) : A), and

dV = Ri(1 ui)R-dui.


By the sequence of relations


y =F-l(1-u),

F(y) = 1- u,

f(y)dy = dui,

dy 1
dui f(y)'

it follows that

dl dF--(1 a )
d f(F-1(1 u) : A)dF-(1 ui)
dui dui

= -f(F-i(1 u) :A) d
du,
f(F-1(1 u) : A)
f(F-(1 u)) '







and

V = R- ( i


Use of these relations in the last integral of (3.2.15) gives


F1 F(F-(l ui): A)Ri(1- ui)R- du

= j F(F-1(1 u) : A)d [- 1( u)-1

= R- F(F-( u,) A)(1 u)1] 1
+ f (F1(1 uj) A) R .-1
(R,1 u) d
I,_i f (F-(1-u)) R4 1


S f(F(1 u ): A u)R- (3.2.16)




R 1 Ju.- f (F-I (1 -)) "u))
[= {F(F-(1I- ui-) : A)(1 us) '-]1


l 1 f(- (1-: ) : )
+ u ) d(F- 1 ) (3.2.16)

Then with the additional relation implied by the definition of Rj in Section 2.2:

m, = R1 Rj-1 1, j =1,..., k,


substituted into (3.2.16), we get


(R1 1)(C, + 1)



R-1
x ." F(F-(1 ui-1 ) : A)(1 ui-) 'l-
Ri 1
-(Ri 1) {Rf(1 u)m du}
wi-2 j=








Ri l f(F-(1 ui) : A) (1
XRi,- 1 f(F-1(1 ui))

=^ 1 1* /'i-2}
= R, Ii 1 i {Ri(1 us)mJdu1}


(1 u.-1)
1 1 i-1

si- j=1
f (F-1( i): A)(1 ) du
f (F-I(1 ui))
= Ri(Ci-I + 1) (ci + 1),


which is just a re-expression of (3.2.12) or (3.2.14) since ci and Ci are of the same

form after integration over ui+1,..., uk.

Now if Ri = 1, we have k = i, and mk = 0. Here, the condition (3.2.12) reduces

to

ck = Ck-. (3.2.17)

The relation (3.2.17) can be verified as follows:

c 1 f(F-1(1 uk) : A)


x f (H-{R (1- u ) dui }duk
lk-2 1 =

-2 1 (1 Uk-1) 1
k-2
xR(k-1)(l U(k-1))1+Mk-I I{R(1 uj)m'duj}duk
j=1
1 .0 [F(F-(1 uk ) : A) -
U-2 J(1 -U k-1)
k-2
xRk-I(1 Uk-1)R-1-1I R( uj)"du}duk
j=1
= Ck-1








Stochastic Integral Form for v


The statistic at (3.2.10) can be readily translated into the form of a stochastic

integral. Recall that the control group sample is labelled sample 0; the treatment

group sample is labelled sample 1.

Recall the notation defined in Section 2.2, and recall the definition of indicator

function I(A) = 1 or 0, according to whether the event A occurs or does not occur.

For the groups r = 0, 1, with survival time random variables


Xr, j = 1,..., N,


and censoring indicators (as defined in Section 2.2)


6,j, j = ,...,


let
Nr
N,(x) = fI(x,j < X6, = 1).
j=1

Note AfN(x) is the number of failures for group r that occur no later than time x.

Also, let
N,
Y.(x) = ZI(Xx, > x),
j=l

the size of the risk set for group r at time x. Note that Y,(x(i)) = Rri in our earlier

notation for risk set sizes. Let


YI() + Yo(x)= Y(x),


n (x) + Ao(x) = A(x),







and

dN,(x) = NX(x) N,(x-).

The assumptions of continuous survival distributions implies that the probability

of ties among the x(i) is zero. Thus with probability 1,

d (x) = Z(i), if X = (i);
0, otherwise,


and
f1 (i), if X = (i);

0, otherwise.
So a stochastic integral expression for v can be written as

= (i) + RoR _Ri\
=1li


= wz(i) wi (1 zA)


k w(x) d (x) (w) d (x)

= ,(z) Yo(X)YY(x) 0Y(x) dYo(z)
-oo Yo(X)) + ( YW) (x) Yo(x) '


(3.2.18)


where


w(x) = ci Ci, X(i) < x < Xi+1.


3.3 Conditions for Asymptotic Properties Under Ho


The formulation of v as a stochastic integral allows us to apply the martingale

theory of Gill (1980) with suitable adaptations. His work includes the statement

of certain conditions that are sufficient to derive an asymptotic distribution for a





50

properly standardized version of v. Recall the definitions of 0(u) and O(u) at (3.2.4)

and (3.2.5), respectively. The notation of 0(u) and 4(u) as score functions that cor-

respond to uncensored and censored observations, respectively, was introduced by

Prentice (1978) in the framework of regression models. Subsequently, the notation

has been used in the area of censored data linear rank statistics (Harrington and

Fleming, 1982; Cuzick, 1985). Thus we adopt the notation for the remainder of this

dissertation.

In this section we lead up to sufficient conditions that permit investigation of the

asymptotic properties of the censored data test based on v. In the process we will

show that for large samples, the expected scores ci and Ci in v can be respectively

replaced with approximate scores that are easy to compute.


Approximate Scores

The computational complexities associated with linear rank procedures that

use expected value scores ci = E[4(ui)] has long been recognized in the literature.

For uncensored data linear rank procedures designated to detect a shift in a dis-

tribution, for example, the normal (van der Waerden, 1953) approximate scores

c, = F-'(1 j ), where 1 F is the cumulative distribution function of the

standard normal distribution, are much easier to evaluate than the expected scores.

In fact, the normal expected scores are the E(Z()), i = 1,... N, where Z(i) is the

ith order statistic in a random sample of size N from the standard normal distri-

bution. These scores involve integrals that do not have closed-form expressions.

More so in the censored data case, the expected scores involve integrals that do





51

not have streamlined closed forms and require numerical integration methods to be

evaluated.

Prentice (1978) conjectured that the expected scores ci and Ci from the rank

likelihood he derived could be approximated by the respective scores 0(1 F(x(i)))

and 4(1 F(x())). A subsequent article by Cuzick (1985) confirms the truth of the

conjecture with the requirement that some fairly mild conditions on the uncensored

score function q(u) be satisfied. The resulting asymptotic equivalence of the linear

rank tests based on the two types of scores is one in the sense that the distance

between the two test statistics converges to zero in absolute mean as N oo.

Before stating Cuzick's (1985) main result, we state two lemmas.


LEMMA 3.3.1 The following relationship holds for i = 1,..., k:

1 1
(u) = i (v)dv.
U Ju

Proof. Utilize the transformation v = 1 F(u) to get


0 (v)dv

1 (f(F-l(1 -v) : A) 1) d
Ju f (F-'(1 v))
=- [F(F-'(1 v): A)] (1 u)

= -F(F-1(0) : A) + F(F-'(1 u) : A) (1 u)

= F(F-(1 u): A) (1 u),


so that dividing both sides by 1 u and substituting with the relation

F(F-'(1 u)) = 1 u completes the proof. O







Lemma 3.3.1 provides a well-defined functional relationship between uncensored

and censored score functions. Mathematical conditions on 0(u) such as continuity

will imply similar ones for (I(u).

Consider the following three sample quantities to estimate the survival function

F(x):

KM(x) = (R-1)(3.3.1)
X(,)< R j
() = (3.3.2)
X(i)) (Ri + 1)
A(x) = exp(- ), (3.3.3)


where Rj is the size of the risk set at time x(j).

The estimator FKM is the so-called product-limit estimator (Kaplan and Meier,

1958). The estimator FP is discussed in Prentice (1978), and fA was proposed by

Altshuler (1970). For generating censored data linear rank test statistics in the case

of location alternatives, a judicious choice from these three estimators has led to

nice closed-form expressions for expected and approximate scores (Prentice, 1978;

Harrington and Fleming, 1982). In numerical computations for large-samples, any

one of the three estimators is reasonable. The actual relationship (Cuzick, 1985)

among the three is

fKM(x) < fA(x)

Unless specified otherwise, F will be the general representation for the three

estimators. One danger in the use of (3.3.1) is when it takes on the value 0 and causes

an infinite-value approximate score. This situation may arise for the normal case





53

for example, since both the uncensored and censored score functions are unbounded

as u -- 1. One remedy in practice is to replace an occurrence of 0 with a value of

0.001 for instance, but this is a very subjective device that can cause considerable

difference in values of the approximate scores. Harrington and Fleming (1982)

employ

=KM (R 1)
X(j) which takes on values in the interval (0, 1]. Both (3.3.2) and (3.3.3) strictly take

on values in the interval (0, 1). Also, (3.3.2) can be regarded as a generalization for

the value

N+1

that is always used in the literature for approximate scores on uncensored data. So

FP is the estimator of choice in practice for this manuscript.

Theorem 3.3.1 below is a modified statement of Theorems 1 and 2 of Cuzick

(1985). The theorem provides us with a set of sufficient conditions for the difference

between v based on the approximate function scores and v based on the expected

scores to be negligible in the limit as N -- oo. The sufficient conditions are fairly

mild; the scores that make up some of the well known linear rank statistics such as

the log-rank, Peto & Peto, and Harrington & Fleming's (1982) GP, 0 < p < 1 class

satisfy them (Cuzick, 1985).


THEOREM 3.3.1 Assume the following conditions on the score function f(u).

C-I The uncensored score function q5(u) is twice continuously differen-

tiable on (0, 1) with first and second derivatives 0'(u) and 0"(u).








C-2


lu'(u)l + lu2q"(u)I < for some a < 1/2 and B < oo.


C-3

lim NVar(-v) > 0.
N-oo N

Then the scores ci and Ci in (3.2.8) & (3.2.9) converge in probability to Q(1 F(x))

and 4(1 F(x)) as N -- oo, respectively. F(x) can be either (3.3.1), (3.3.2), or

(3.3.3).


Proof. Refer to Theorems 1 and 2 of Cuzick (1985). The fact that q(u) can be

differentiated twice with continuity maintained will imply the same properties for

Q(u) from Lemma 3.3.1. 0

The general forms of the derivatives of 0(u) are messy, so that the score functions

for specific distributional choices must be checked to see if C-1 and C-2 are satisfied.

The non-vanishing Condition C-3 on the variance will follow from the structure

obtained when asymptotic properties of v are established in Section 3.4. Cuzick

(1985, Theorem 3) indicates that C-3 is satisfied for such a structure of the variance.


Gill's Conditions

Theorem 3.3.1 brings us to the point where the martingale-based results of Gill

(1980) can be used to establish an asymptotic variance for v as well as normality

(under the null hypothesis of equal survival functions) for its asymptotic distribu-

tion. The usual random censorship model (cf. Section 2.2) is assumed.







The stochastic integral form for v in (3.2.18) can also be considered in the form

J(o ( dA/,(x)) /o(x) (3.3.4)
-co Ytl() Yo(x)

where

K(x) = w(x) Yo()+Y () (3.3.5)
Yo(z) + YI(x)
is a weight function in the class CK of Gill (1980). Gill (1980) defines members K E K

as a function of the observations that equals zero whenever min(Yo(x), Yi(x)) = 0.

The paper of Andersen, Borgan, Gill, and Keiding (1982) shows that the class

of statistics from Prentice (1978) that uses the FP estimator can be written as

a stochastic integral of the form (3.3.4) with K(x) as in (3.3.5). Moreover, the

Prentice (1978) class is a subset of the Prentice and Marek (1979) class based on

the "preservation of scores" condition at our (3.2.12). The Prentice and Marek

(1979) class can likewise be written in the framework of (3.3.4) and (3.3.5).

Gill (1980, p. 72) provides three conditions that are sufficient for the asymptotic

normality of test statistics of the stochastic integral form (3.3.4). These sufficient

conditions can be applied with many distributional forms for the survival and censor-

ing variables, and any test statistics with weight functions K(x) that are members

of the general class )C. We state Gill's (1980) conditions as they are relevant to our

case under the null hypothesis.

Let 1* be the set with membership


{ x I min(Fo(x) > 0, F(x) > 0) },


(3.3.6)








where


Fo(x) = F(x).Lo(x),

PF(x) = G(x) LI(x).


Let A,(x), r = 0, 1 be the cumulative hazard functions associated with the control

and treatment groups, respectively.


1. For r = 0,1:

a. A,(x) is finite on 2*.

b. K2(x)/Y,(x) converges uniformly in probability to h,(x) as N -- oo on each

closed subinterval of Z*. The function h,(x) is left-continuous, bounded, and has

right-hand limits on each closed subinterval of Z*.

c. Yr(x) --+ oo in probability as N --+ oo for each x E Z*.


II. Let S = sup 2'. If S i Z*, then for r = 0, 1:

a.


h,(x)dA,(x) < oo.


lim lim sup Pr(
xTS N--oo J[,S]


for every e > 0.


II. If S < oo, then for r = 0,1:


J(,oo K2(x)/Yr(x)dA,(x)

converges in probability to 0 as N -+ oo.


K2(t)/Y((t)dA,(t) > e) = 0







When conditions I, II, and III hold, two consistent estimators for the variance of v

are
-1 _-o [K2(z)] d(N'r(x)
V = X) (3.3.7)
Y, -o L(x) JY.(X)
and

=1 K (x) d(Nx (x) +ANo(x))
V2o =- 0 yo ()J Yi(x)+Yo(x)

= 2(x)o d(AN (x) + Ko(x)). (3.3.8)
[-oo Yr(x)Yo(x)J

The variance estimators at (3.3.7) and (3.3.8) are suggested by Gill (1980, p. 47).

Lemma 4.3.1 of Gill (1980) establishes that both (3.3.7) and (3.3.8) are consistent

estimators under Ho for the true limiting variance of v based on the form (3.3.4).

Gill (1980) notes that there is no true ordinal relationship between V, and V2, and

we would expect them to be fairly equal in practice for large samples. For the null

hypothesis case, there is some creedence to choosing V2 on the basis that it utilizes

both samples to get a pooled-type of estimator of the common cumulative hazard

function A(x).

In order to verify the three conditions of Gill (1980) and thus obtain variance

expressions and asymptotic normality of v, we consider some mathematical results.


LEMMA 3.3.2 (A continuous function preserves uniform convergence.)

Let {fN(x)} be a sequence of random functions that converges uniformly in prob-

ability to f(x) as N -+ oo for x E some set E. If g(.) is a continuous function

on the range of {fN(x)}, then g(fN(x)) is uniformly convergent in probability to

g(f(x)) as N -, oo for x E E.








Proof We know that for arbitrary 6 > 0,


Pr(sup IfNv(x) f(x)I > 6) -, 0 as N -- oo.
xEE

Let e > 0 be given. Since g(-) is continuous, we can find 6 > 0 such that Ig(fN(x))-

g(f(x))| < e if IfN(x) f(x)| < 6. Thus for arbitrary e,


Pr(sup Ig(fN(x)) g(f(x))| > e) = 1 Pr(sup Ig(fN(z)) g(f(x))l < e)
xEE zEE

S1 Pr(sup fN(x) f(x)j 6)
xEE

= Pr(sup fN(x) f(x) > 6)
zEE
--- 0


as N -- oo. O


LEMMA 3.3.3 Let {AN(x)} be a sequence of random functions that is uniformly

convergent to A(x) in probability as N -- oo. Let {BN(x)} also be a sequence

of random functions that uniformly converges to B(z) in probability as N -- oo.

Assume that A(z) and B(x) are bounded for all x E E. Then AN(x)BN(z) converges

uniformly in probability to A(x)B(x) as N oo.


Proof Let e, c > 0. Then


Pr(sup I(AN(x) A(x))(BN(x) B(x))I > e)
zEE

= Pr(sup I(AN(x) A(x))(BN(x) B(x))\ > e,sup IBN(z) B(x) <5 e/c)
zEE zEE

+ Pr(sup I(AN(x) A(x))(BN(x) B(x))l > e,sup IBN(x) B(x)I > c/c)
zEE zEE

< Pr(sup I(AN(x) A(x))I > c)
zEE








+ Pr(sup IBN(x) B(x)I > e/c)
xEE


-- 0+0=0.


(3.3.9)


The boundedness condition implies that IA(x)l < M for some positive number

M < oo. It is also assumed that


Pr(sup IBN(x) B(x)| > -) -- 0.
xEE M

Combining these last two facts with the relation


Pr(sup IA(x)[BN(x) B(x)]j > e) < Pr(sup IBN(x) B(x)I >
xEE xEE M

implies the result


Pr(sup IA(x)[BN(x) B(x)]l > e) --- 0
xEE


(3.3.10)


as N -* oo.


Commuting the roles of the two sequences {AN(x)} and {BN(x)}


similarly gives


Pr(sup IB(x)[AN(x) A(x)]| > e) -- 0.
xEE


(3.3.11)


Next employ the identity


AN(x)BN(x) A(x)B(x)

= (AN(x) A(x))(BN(x) B(x)) + A(x)(BN(x) B(x))

+B(x)(AN(x) A(x))


along with (3.3.9)-(3.3.11) to give


Pr(sup IAN(x)BN(x) A(x)B(x)I > e)
xEE








< Pr(sup I[AN(x) A(x)][BN(x) B(x)]l > )
xEE 3

+ Pr(sup I[AN(x) A(x)]B(x) > -)
zEE

+ Pr(sup IA(x)[BN(x) B(x)] > )
xEE 3

--40+0+0=0


as N oo, which is the desired result. C


3.4 Asymptotic Normality of v


Recall that Theorem 3.3.1 provides a set of sufficient conditions whereby the

expected scores in the censored data rank statistic v can be replaced by approx-

imate scores for large samples. The test statistics considered by Gill (1980) in

establishing asymptotic properties can all be regarded as censored data linear rank

statistics based on approximate scores. Therefore, in the development of asymptotic

properties for v that follows, we will consider the version of v that is based on the

approximate scores, i.e.

k
V = z(qw(1 F(x())) + MOi(1 F(xi)).
i=1

Under the conditions of Theorem 3.3.1, the same properties for v based on the

expected scores (as in (3.2.2)) will follow.







Verifying the Conditions

Gill (1980) used the log-rank statistic as a prominent member of the class K:.

Among the many properties he explored for this member, he showed the meeting of

the three conditions listed on page 56 of Section 3.3 that are sufficient for a limiting

normal distribution of the properly standardized version of the statistic under the

null hypothesis of equal survival distributions. In the form (3.2.18) for v, setting

w(x) = 1 gives the log-rank statistic. The corresponding weight function in the

class KC is
Yo(x)Yi(x)
KC(z) = Y( Y() (3.4.1)
Yo(x) + y,(x)
If we multiply Kc(x) by the weight function

Sf(F-1((x)) : A) F(F-((x)):A) (3.4.2)
f(F-1(F(x)) F(F-1((x)))

for our model at (2.2.4), we get a weight function K(x) that is a member of Gill's

(1980) class KC. The corresponding function tb is random since it is a function of

the approximate scores 0(1 F) and 4(1 F). Note that w(x) at (3.3.5) is not

random as it is a function of the ci and Ci. Convergence properties associated with

tb(x) at (3.4.2) in combination with results already well-established (Gill, 1980) for

the log-rank statistic will provide the course for verifying the three conditions that

are sufficient for asymptotic normality of v.


LEMMA 3.4.1 Suppose that f(t : A),A > 0 and f(t) = f(t : 0) are continuous

densities with support over the interval (-oo, oo). If A1 < oo and A2 < oo are








positive constants such that

f (t : A) f (t : A)
lim f A1, and lim = A,
t-oo f(t) t--oo f(i)

then ti(x) defined at (3.4.2) is bounded on the interval (-oo, oo).


Proof. By L'Hopital's rule,

im F(t : A) l f(t : A)
km = hm = Ai.
t-oo F(t) t-foo f(t)

Therefore,

lim f(t : A) F(t: A) limf(x : A) limf(t: A)
lim = lim lim
t-oo f(t) F(t:) t-oo f(x) t-oo f(t)

= A -A =O0.


Also,

lim f(t:A) F(t : A)} = f(t: A) li F(t: A)
hlm- = lim hm
t---oo f(t) F(t) t.--,o f(t) t---oo F(t)

SA2-1 < oo.


Now since
f(t : A) F(t : A)
f(t) F(t)
is continuous, then for any finite values a, b, the function (3.4.3) is bounded on every

finite interval [a, b]. Since (3.4.3) is finite at the points -oo and oo, the substitution

t = F-'(F(x))


shows that ib(x) at (3.4.2) is bounded on (-oo,oo). 0

The value of the Lemma 3.4.1 will be seen when we choose specific forms for

F(x : A), but it should be noted that it does not cover the case where both the








censored and uncensored score functions tend to infinity as x tends to infinity. For

this case, the "indeterminate" form oo oo for the "limit" of tb(x) requires special

handling. An example of this occurs in Chapter Four.


THEOREM 3.4.1 (Uniform convergence in probability of the Kaplan-Meier esti-

mator.) Assume the model outlined in Section 2.2, with the support of G(x) to be

(-_0, oo). Let s E (-oo, oo) be such that the risk set size


Y(s) = Yo(s) + Yi(s) c0. (3.4.4)

Then under the null hypothesis of F(x) = G(x) for all x, the Kaplan-Meier estima-

tor FKM converges uniformly on x E [-oo, s] in probability to F as N -- oo. That

is,

sup FKM(x) F(x)j ) 0.


Proof. See Theorem 4.1.1 of Gill (1980), who proves a more general case. His

notation uses F(x) for the cumulative distribution function. The relation (3.4.4),

which is given as Condition Ic of Gill (1980), has the interpretation that the size of

the risk set at any point x grows to infinity as N -+ oo. O

If the support of the censoring distributions is also (-oo, oo), then s = oo.

Sometimes, however, censoring distributions are assumed to have support of the

form (-oo, s), where s < oo, and examples can be constructed to show that the

uniform convergence of FKM fails for x > s.

COROLLARY 3.4.1 Theorem 3.4.1 holds for FKM(x) replaced by either FP(x) or

FA(x).








Proof. The case for FA is also covered in Gill's (1980) Theorem 4.1.1. For the

estimator FP, first consider the following relation from the lone lemma of Cuzick

(1985):

IPP(x) FKM(X) PP(X) 2 (3.4.5)
Y()" (3.4.5)

Then


sup ) P(x)- F(x) = sup IP(x)- FKM()+ FKM(x) F(x)[
-o
< sup PP(x) FKM(x)I

+ sup FKM(x)-F(x)
-oo P
-+0+0=0


since

sup IFKM(x) F(x)j I 0
-oo
by Theorem 3.4.1 and


sup FP() FKM(x) < sup (x).--2
-oo<
< 2/ inf Y(x)
-oo<0 P
-+ 0


by (3.4.4) and (3.4.5). 0

Using these last two results, we now consider a key property for the weight

function tb(x) at (3.4.2).


THEOREM 3.4.2 Assume the conditions of Theorem 3.4.1 and Lemma 3.4.1.

Then the weight function i(x) represented by (3.4.2) is bounded and tZ converges







uniformly in probability to w* on (-oo, oo) as N -- oo, where


f(x : A) F(x : A)
w'(x) = (3.4.6)
f(x) F(x) (3.4.6)

Proof Since F(x) is assumed continuous, its inverse function F-'(x) is also con-

tinuous. The function

f(F-'(.) : A) F(F-'(.) : A)
f= (F-'(.)) F(F-'(.))

will also be continuous since it is a composite function of continuous functions. The

survival function estimator F takes on values in the interval [0, 1], so Lemma 3.4.1

insures that tb(x) is bounded when it is defined on the extended line [-oo, oo].

Applying Lemma 3.3.4 with (3.4.7) in the role of the continuous function and F(z)

as the argument, where P has the uniform convergence properties in Theorem 3.4.1

and Corollary 3.4.1 proves the uniform convergence of tb(-). 0

As mentioned previously, the three conditions of Gill (1980) have been discussed

and verified for the member Kc(x) which corresponds to the log-rank statistic.

Actually, Gill (1980) attaches a standardization factor on to the weight function at

(3.4.2) to get
NoN, Yo(x) Yi(x) No + N
S No +N, No N, Yo(x)+ Y1(x)

The multiplicative factor is attached to ensure that the variance of the test statistic

corresponding to K.(x) is bounded away from 0 and oo as N -+ oo. Note that this

provides a test statistic
No + N,
v = -N V
NoV N








where v remains defined as in (3.2.10) and (3.2.18). The variance estimators V1 and

V2 respectively given by (3.3.7) and (3.3.8) can be adjusted accordingly, and their

consistency for the variance of v* is established in Lemma 4.3.1 of Gill (1980). That

lemma is a precursor to Gill's (1980) Corollary 4.3.1 and Proposition 4.3.3, which

specify the asymptotic distribution for the test statistic based on 1Kf(x).

The standardization factor of Gill (1980) is specifically

No + N,


The previous paragraph defined the relationship between v and v*. Suppose there

exists a variance of v*, Var(v*), such that

v*
Var(v*)

is a random variable with some asymptotic distribution. Also suppose that the

variance estimators Vi and V2 are such that

S No + N1
V N NV,
No N1
S=No + NV
2 NoNx

are consistent estimators of Var(v*). By Slutsky-type arguments,
V* V* V*
S and and-
Var(v*) I VA

will have the same asymptotic distribution. But note that

V V
Var(v*) Var(v*)
V* V
1 and


vW~7
We V-V2







so there are numerous expressions of random variables that are asymptotically equal

in distribution.

The proofs and surrounding discussions of Gill's (1980) Corollary 4.3.1 and

Proposition 4.3.3 note that

sup Y() x) 0; r = 0, 1, (3.4.9)
-oo<;
where F,(x) = Pr(X,i > x) as introduced in Section 2.2, and

N,
min(No, N1) oo; N---o -' pr E (0,1) (3.4.10)
No + N1

are sufficient to establish conditions I-III for various censorship models and thus

the asymptotic distribution of the log-rank statistic. The Glivenko-Cantelli theorem

can be used to show that (3.4.9) is satisfied for the mixture model at (2.2.4) under

the random censorship model. (Gill, 1980; Harrington and Fleming, 1982).

THEOREM 3.4.3 Assume the random censorship model described in Section 2.2,

and let (3.4.10) obtain. Suppose zb(x) is defined by (3.4.2), Kc(x) is defined by

(3.4.1), and KI(x) is defined by (3.4.8). Let Z* be defined as in (3.3.6), and suppose

tb(x) is bounded on 1*. Then the test statistic

= No + N No + N, kr R1i
0 =R1 NNV= N1

will satisfy Conditions I-III on page 56 as they are required. Define
f( :' ( A) F(x1: w) 0
Var(') f(x : A) F(x : ) o(x)() i dA(x). (3.4.11)
-oo f() F(x) Po oW(x) + ph i (x)

Recall the mixture model at (2.2.4). Under the null hypothesis 7r = 0,

V* V
Var(v*) N Var(v*)
Vr~r(V) =7-N&+-N,=lV







converges in distribution to a standard normal random variable as N oo. Fur-

thermore, both estimators

V11 2 (X) Y_,(x) d,( ()
r=o = Y0 (x) + Y (x). d,(

and
V2 = 1_ tb2(x) Y d(Ao(x) + AN(x))
-(Yo(x) + YI(x))2
will be such that
No + N, No + NV
NoN, NON,
converge in probability to Var(v*) as N -- oo.

Proof Under the null hypothesis r = 0 and the random censorship model outlined

in Section 2.2, Conditions (3.4.9) and (3.4.10) are sufficient for conditions I-III to

hold for Kc(x). We start with verification of Condition Ia. For those values of x

in I* such that min(Fo(x),Fi(x)) > 0, both F(x) > 0 and G(x) > 0. Thus the

corresponding cumulative hazard functions will be less than infinity, i.e. finite on I.

In Condition Ib, let

K ,(X) = l (x) "W

Theorem 3.4.2 and Lemma 3.3.2 imply that

p f(x : A) F(x : A)
S f(x) F(x)

uniformly on [-oo, oo) as N -+ oo. The uniform convergence will hold on closed

subintervals of 1* as well. Applying Lemma 3.3.2 with


AN(X) = -(x)







and

BN(X) = K; (x)

gives

K2(x)/Y,(x) h,(x); r = 0,1

where

,r) { f(x : A) F(x : A) 1p2 P Fo(x)F(x) 120
X fF (x) F(x) ',() poLo(x) + pix) ( r
(3.4.12)

uniformly on closed subintervals of Z* as N -- oo. Let

h( ,() poFo(x) + pF(x)

be the corresponding function for KI(x). Then hr is the product of hc and the

square of expression (3.4.3) from Theorem 3.4.2. It is the product of two bounded

left-continuous functions with right hand limits, and thus is itself a bounded left-

continuous function with right hand limits.

Condition Ic is covered automatically by the random censorship model (Gill,

1980).

Theorem 3.4.2 implies there is a positive number M1 such that

f(x : Z) F(x: ) < M for all x E [-oo, oo],


and therefore

h,(x)dA,(x) = H(.{ -2 h} ()dA,()

< M, hc(x)dA,(x) < oo,







so that Condition IIa would be satisfied if S Z*, since


j h(x)dA,(x) < o0


was established for the log-rank statistic in Gill (1980). Analogously, there is a

positive number M such that zi2(x) < M, so Condition IIb follows from


liimlimsupPr( I K(x)/Yr(x)dAr(x) > e)
xTS N-.oo Jx
< limlimsup Pr( MK2(x)/Yr(x)dA,(x) > e)
-zS N-oo Jx
= limlimsupPr(M / K2(x)/Yr(z)dAr(x) > e)
xTS N-*oo J
= limlimsup Pr( K[ 2(x)/Y,(x)dA(x) > --)= 0,
xTS N-oo Jx M

the last step verified by Gill (1980).

The bound M used in the verification of Condition II also is central to a veri-

fication of Condition III if S < oo. Finally, the expression for Var(v*) comes from

substitution of (3.4.12) into Gill's (1980) expression


f_ (hi(x) + ho(x))dA(x)

in his Corollary 4.3.1. The expressions for the estimators V1 and V2 are determined

after substitution of

b(x) Kc(x)

for K(x) in (3.3.7) and (3.3.8). The convergence associated with V1 and V2 follows

from Gill's (1980) Lemma 4.3.1. 0








COROLLARY 3.4.2 Under the conditions of Theorem 3.4.3,

v v
and


converge in distribution to a standard normal variable as N -+ oo.


Proof. Recall that

V* =N Vt N ; =1,2,
N, No

in the discussion before Theorem 3.4.3, and apply a Slutsky-type argument. 0

The expressions given in Corollary 3.4.2 are most convenient for calculating

the statistic on data. If the support of the survival and censoring variables is

(-oo, 00), then S = oo, and Condition III will then be empty. This is also true if

no censoring occurs. On the other hand, it is often tenable in practice to assume

uniformly distributed censoring times with finite support. In this case Condition

III is required, as S < oo.


Use of the Test


Back in Section 2.2, the mixture model (2.2.4) was introduced with the pre-

sumption that A > 0, i.e., that larger values of the response were associated with

the treatment group (See Assumption A2). The asymptotic normal distribution of

the test statistic developed in Theorem 3.4.3 suggests that the opposite situation

of smaller values (A < 0) can be handled as well, as long as the required conditions

hold. Note that the special case of Theorem 2.3.1 is included here.

If a test against the alternative


with strict inequality for at least one x,


G(x) F(x),








is desired, the rejection region will be in the lower tail of the standard normal

distribution. For A > 0, the upper tail is appropriate. Absence of any knowledge

about A should have a rejection region involving both tails.

It is not true, however, that v or the test statistic that is a standardized version

of v is an odd or even function of A. The fact that v is not a symmetric function

of A gives another aspect in the consideration of the choice of A for conducting the

test. However,
k
(ci + miC.) = 0 (3.4.13)
i=1

holds, since the sum (3.4.13) is the average of sums of scores that occur from all

possible underlying rank vectors given the data (Prentice, 1978). Note that (3.4.13)

implies

k k
v = z(ici + MC) = ((1 z))c + (mi- Mi)C) (3.4.14)
i=1 i=1

Hence summation of the scores assigned to the control group observations (when

A > 0 is employed) produces a small value for an appropriately standardized test

statistic that could be compared with the lower tail of the standard normal distri-

bution.

If larger values for the control group are present, the assigned scores for the

control group will likewise tend to be larger than those scores for the treatment

group. Then v (cf. 3.4.14) based on the treatment group scores with A > 0 will

tend to be small, and the test statistic in Theorem 3.4.3 should be compared with

the lower tail of the standard normal distribution. Summing the negatives of the

scores in (3.4.14) would produce large values of the test statistic based on v, and








the rejection region should then be based on the upper tail of the standard normal

distribution. This approach was suggested by Conover and Salsburg (1988) for

their scores derived from Lehmann alternatives and uncensored data. Therefore, if

smaller values of the response for the treatment group is of interest, Theorem 3.4.3

permits us to either


1. Choose a value of A < 0 to calculate the scores, and compare v with the lower

tail.


2. Take the negatives of the scores based on a A > 0, and compare v with the

upper tail.


3. Take the scores based on A > 0 and compare with the lower tail.


Choices (2) and (3) will be equivalent since the rejection regions are based on the

standard normal distribution.


Dealing with Ties


Those who are practitioners of statistics know that ties in the observed data are

often prevalent. Continuity assumptions on the survival and censoring distributions

imply that the probability of ties is zero, but measurement error forces us to group

the data at plausible times. Let dl(,) denote the number of observed failure times

in the treatment group at time z(i), and let d(i) be the total number of observed

failure times at x(;). The test statistic v as in (3.2.10) can be modified by the usual








convention (e.g. Prentice and Marek, 1979):


v = ( (( d( i)-L). (3.4.15)
i=1 R.

The stochastic integral form (3.2.17) already covers the modification as does the

expression (3.4.11) for the limiting variance. Now define


AAV.(x) = X.((x) X.(x-)


to be the number of failure times at x that belong to treatment group r, r = 0, 1.

(Note that A is not related to the parameter A.) The variance estimators are

modified as

= J W() Yo(x) + Y(x) ~ Y(x) --1
r f00 .^OW + Yr(X)-

and

00o Yo(x)Y&(x) 1W) + &V W 1()
V2= t 2(x) YOx)Y() 1 Wo(x)+ A'(- 1) W d(Afo(x)+Ni(x)).
=J-o (Yo(z + Yi())2 Yo(x) + Yi(x) 1

It is also mentioned that if all the ties at a particular failure time belong to the same

group, the modifications are not needed, since v can be computed with a breaking

of the ties in some arbitrary order. Ties among censoring values are not a concern

since they are all assigned the same scoring value within the interval defined by

adjacent uncensored values.

By the same arguments in establishing (3.2.18) for v, the variance expression V2

is equal to

i ,? 1- R i Ri }d(i) (3.4.16)
i=l \i RR Ri 1





75

with 0/0 = 0 and tb = (x(;)) 4(x(i)). When there are no ties in the observed

data, (3.4.16) reduces to


wtR, 1 (3.4.17)

Expression (3.4.16) has often been interpreted in the literature as a weighted sum

of hypergeometric variances because of the argument of Mantel (1966) in deriving

the log-rank test from a series of independent 2 x 2 contingency tables.


3.5 Evaluation of Expected Scores


The forms of the expected scores in (3.2.4) and (3.2.5) produce very involved

multiple integration when some of the mj are nonzero if we approach the evaluation

in a brute-force manner. But suppose we assume that 0((1 ui)) = 1 in (3.2.4).

Then the integration is straightforward (Prentice, 1978) and equals the value of 1.

This suggests that
k
g*(ul,...,uk)= II Rj(1 uj)m", 0 < u < -- < uk < 1
j=1
constitutes a joint density in the uis. Since the expected scores involve score func-

tions that only depend on a particular ui, the scores c, and C, can be represented

as

ci = (ui)g;(ui) du,; (3.5.1)

C, = 4 (u)g*(ui) du,, (3.5.2)

where
k
g;(u,) = J.* J I Rj(1 uj)'mdu, ... d. ddui+ ... duk (3.5.3)
ul<-.-







is the marginal density in ui corresponding to the joint density g*(ul,..., uk). It

turns out that for the score functions considered in this dissertation, the integrals

in (3.5.1) and (3.5.2) do not have nice closed-form expressions. But numerical

evaluation of the integrals can be carried out in a straightforward manner.


The Form of gf(ui)


To gain some insight, consider the case i = 1. Integration over u2,...,uk in

g*(u,. ,uk) yields


g (ui) = ... {R,(1- uj)m-duj} = R1(1 -u1)R-1,
uk-1 u1 j-'

To obtain g2(U2), we can integrate out u3, ,uk and then ul:

1 1 u2 k
g(u2)= 1 ..jJ1{RA(1-u,)mdu,}
Uk-1 u2 0 j=l
u2
= RR2(1 u2)R2-1 (1 u)m(')du1
0


O < ul < 1.


U2
= RR2(1 u2)R2-1 J(1 u1)R-R2du
0
= R1R2(1 u2)R2-1 1 1 (1 u2)R-R2]

= RR2 (1 u2)R2-1 (1 u2)R-1
SR1 R2 R+ -- R "

For i = 3, the housekeeping becomes more extensive. We get

S 11 u3 u2 k
g;(u3)= -J J JI {Rj(1 u.)mrdu.}
Uk-1 U3 0 0 j=1
u3 u2
= RIR2R(3)(1 u3)3)- //(1 u2)m((1 u1)m()duldu2
0 0
= RlR2R(3)(1 u3)R3-1







u3
xI(31 /R1

= RRR3(1 u3)R3-1 (R R2) (1 u2)-R3- du2
0
-R1R2R3(1 u)R3-1 (R- ) (1 U2)R-R-Id
= R1R2R3(1 -u -


S R2)(R2- R3)
-RIR2R3(1 u3)n3-1

SIf--(I--u3)R-R3}
S(R R)(R R3)
= R1R2R3(1 U3)R3-
[ 1 1 (1
x(R, R2)(R2 R) R2) R3)

+R1R2R3(1 u3)R2-1 1
(R (R, R)(R2 R)
= RR2R3(1 3 )R-1 1

(R- )R)(R3 R3)]
= (Rx,( R2))"(R- (RI R2)(Rs R3 )
+R R2R3(l U3 R2-11
(RI R2)(R R2)]
+R1R2R3(1 u3)R1 -(R1 R)R R)

1R23(1 U3)R- (R2 R)(R3 R1)

A reasonable conjecture then for arbitrary i in (3.5.3) is



1=1

The validity of (3.5.4) can be proven by mathematical induction. We start with a


result that will be used in the proof.





78

LEMMA 3.5.1 The risk set sizes


R, i =l ,...,k+ (Rk+ 0),


satisfy
1 1
= i+1, i= ,...,k.
S(RI -=) (R, R,)
I=1 =11

Proof. The product term in the denominator of the left hand side can be regarded

as a polynomial in Ri+, with the simple roots R1, R2,..., Ri. Then the whole

expression on the left hand side is a ratio of two rational functions. Since the

denominator is a polynomial, we can decompose it into more elementary functions

that involve the factored terms. A discussion of the technique can be found in

Gradshteyn & Rhyzik (1980, p. 56-57). The following notations of f and 0 mimics

theirs and is to be assumed only in the local context of this proof. Denote


f(R) = H(R- Ri);
1=1
(R) =


as the two rational functions. Then

f(Ri+x) A1 A2 Ai
= + +-..+
f/(R+l) Ri+l R Ri+l R2 Ri+ Ri'

where

A- (R1) A (R2) = (Ri)
f'(R1)' f'(R2)' f'()

Now


f(Ri+,) = (Ri+1 RI)(R.+i R2) ... (R?+l -R),










i
f'(Ri+l) = 1(Ri+e R,) +
I=1
which implies that
which implies that


f'(R1)


f'(R2)




f'(Ri)


i i
j(Ri+ Ri) + + JQ(Ri+ Ri),
1=1 I11
1 2 1ii


= l(R RI),
1=1

1#1

i
= ll(R2- R),


1=1
1;2



-- II(R, RI,)


as all other terms drop out. Since O(Ri) = 1, 1 = 1, -, i, we have




L=1
f(Ri+i) 1
f (A+I) (-+i Ri)(I (Ri Ri)
11


1


ft
( +l R4)( H (Ri Ri)




i+1 i+1
I (Rt R1) 1 (li
1=1 I=1
19d1 10i


1 1
(1)i-1 +1
j=l n(RI Rj)
1=1

Coupled with the fact that


f(R+1)
1(Ri+1)


1
(-1)i


we get the desired equality. 0







As a first step in the induction argument, note that (3.5.4) holds for i = 1. Next

assume that (3.5.4) holds for i. From this assumption it must be proven that a

version of (3.5.4) with i + 1 replacing i everywhere is also true.

From the joint density in the u1,... U, we need to integrate out ul,..., ui (call

this "subrange 1") and u(i+2),..., uk ("subrange 2") in order to obtain the marginal

density g,'1 (ui+1). Integration over subrange 2 yields


Ri+ (1 u+)R+,1-1 /** f Rj(1 uj)dui. (3.5.5)
subrange 1 j=1

To see what happens over subrange 1, write (3.5.4) as



R,(1 ui)-1 R ,) E i. (3.5.6)
1= / i (Rt Ri)


Note the similarity with (3.5.5). Because we are assuming the case for i is true, the

expression



('= l =1 \ J (R1 Rj)
1;1
in (3.5.6) is the value of the integral of g*(u, ..., uk) over u1, ..., ui-1. The subse-

quent integration of (3.5.7) over ui produces


Rj,' (1 u,)R-Ri+-'du,
i=l = I (R i- Rj) o
1t$

= R- (R) -(1 U+)R-'+] (3.5.8)
= x (R, R -) R- R+i+
'= 1








The substitution of (3.5.8) into (3.5.5) gives



1=1
( ,) (1 -R u +l)+Z- I (i) l R (1 ui+i)R 4 J+1 1
\' =1 (R Rj) (R,) R) R Ri+-


1 i+ 1R-1 i+ Ri+I-1
= Ii+ i+
\'=+1 j=' n (RI Ri) i=' n (RI Ri)



= R(j,) i+1 + i+ I (3.5.9)
'= i= H (Ri Rj) l (Ri Ri+i)
1=1 1=1
10i IJi+l
with the last step arising from substitution of the equation in Lemma 3.5.1 to get

the last term on the right hand side of (3.5.9). Collecting the i + 1 terms in (3.5.9)

into one summation gives

i+1 i+1 ui+R-l

'= j= (RI Rj)

which is the density in ui+1 that matches the form (3.5.4) for u,. This completes

the induction argument that (3.5.4) holds for all i > 1.

Although the form gf(ui) in (3.5.4) is not simple, analytical or numerical eval-

uations of ci and Ci will involve single integrals.


3.6 Properties Under H,


The behavior of the linear rank test statistics derived in previous sections can be

studied in terms of (Pitman) asymptotic relative efficiency (ARE). The structure of

local alternatives of parameter values {7rN} converging to the null hypothesis value

ro = 0 will allow us to compare the local powers of v for different scores.








Gill's (1980) foundational work will again be applied. In particular, his Chapter

Five provides sufficient conditions for asymptotic (N -- oo) normality for stan-

dardized v under a sequence of local alternatives in the location-shift model. Gill's

(1980) results can be used to evaluated the "efficacy" of the linear rank test statistic

based on v and the sequence of local parameter values. The Pitman ARE of one

test with a competitor can be established by evaluating the ratio of their efficacies.

The efficacies in general depend on the censoring distributions for the two sam-

ples. Thus we can study the influence of censoring distributions on behavior of the

tests. For the exponential distribution (extreme-value in the logarithmic scale) it is

known that fixed (not dependent on N) and equal censoring distributions for the

control and treatment populations are sufficient for the log-rank to be fully efficient

(Crowley and Thomas, 1975). Gill (1980) extended this result to other distribu-

tional forms including the logistic, double-exponential, and normal distributions.


The Structure of Local Alternatives


Let { r)} denote a sequence of parameters belonging to (0,1] where

a


for some constant a > 0. This choice has been used by authors in the uncensored

data case (Johnson et al., 1987). When convenient, the value of a = 1 can be

assumed without loss of generality. The sequence of corresponding control and

treatment population survival functions is


FN(x) = F(x) (unchanged from Ho)







GN(x) = 7rNF(x: A) + (1 rN)F(x).

Consistent with previous definitions, the respective cumulative hazard functions are

AN(x) = -log(F(x)) and A(x) = -log(GN(x)).


Sufficient Conditions

In sections 3.3 and 3.4 of this manuscript, Gill's (1980; p. 72) conditions sufficient

for a limiting null distribution were stated and verified for v in the mixed model

at (2.2.4). Under a sequence of local alternative parameter values, Gill's (1980)

conditions on his page 106 in addition to those given on his page 72 (Gill, 1980)

will have to be verified in order to establish asymptotic properties.

We adopt the notational convention of Gill (1980) with suitable modifications

for stating these conditions. To deal with local alternatives, certain parts of the

conditions in our Section 3.3 must be replaced with more general statements. The

following is a list of Gill's (1980) conditions stated in terms of our mixed model

setup (2.2.4).

I'. There exist 7,(x) such that

7,(X) = lim i 1 r = d0, 1
N-o No + N1 dAo =/

uniformly on each closed subinterval of {x : F(x) > 0}. Also, let

7(x) = 7o(x)- -i(x).

Let k(x) and

K(x) = t(x)K(x) = t(x) YO Y ()
Yo(x) + Yi(x)








be such that

No + NM
lim N + K(z) = k(x)
N-.oo NoNi

uniformly in probability on closed subintervals of


T = {x | min(Fo(x) > 0, F (x) > 0)}.


The function k(x), called a "limiting weight function" by Gill (1980), is left contin-

uous with right hand limits such that


k+(x) = lim k(t)
t-*x+

is of bounded variation on closed subintervals of Z*. The function k(x) is defined

to be zero in regions outside of 2*.

a. FN(x) converges uniformly on Z* to F(x) as N --+ oo; GN(x) converges uniformly

on I" to G(x) as N -- oo. Also,


A,(x) = lim AN(x)
N-oo

is finite on Z*.

b. K2(x)/Y,(x) converges uniformly in probability to hr(x) as N -+ oo on each

closed subinterval of 1*, where h,(x) is left-continuous and has right-hand limits on

each closed subinterval of 2*. Also,


lim h,(t)
t-r+

must be of bounded variation on each closed subinterval of Z*.

c. Y,(x) oo in probability as N -- oo for each x E Z*.








II'. Let S = sup Z*. If S I Z, then for r = 0, 1:

a.

/. h,(x)dA,(x) < co.



b.

limlimsup Pr(/ K(t)/Y(t)dAN(t) > e) = 0
xTS N oo J[x,S]



for every e > 0.


III*. If S < oo, then for r = 0,1:


S,oo) K'(x)/Y)(x)dA(x)


converges in probability to 0 as N -+ oo. From page 106 of Gill (1980) the extra

conditions are


IV'. If S I', then for r = 0, 1:

a.


Ik(x)y,(x)l dAo(x) < oo


lim lim sup Pr(
zTS N-oo J[z,S]


IK(t)l IdA'(t) dAo(t) > )= 0


for every e > 0.








V'. If S < oo, then for r = 0,1:


JS,oo) K(x)I IdA(x) dAo(x)I

converges in probability to 0 as N -+ oo.


Some of the components of II* and III* are essentially no more than a substitu-

tion of A (x) for Ar(x) in conditions II and III. Also, note that


AN((x) = Ao(x) = A(x).


In order to verify I*- V* for the mixed model setup, we follow our strategy in the

null hypothesis situation, where each condition was verified in two steps:


1. Establish that such conditions have been verified by Gill (1980) for the case

K(x) = Kc(x) (log-rank); and


2. Use (1) along with the fact that our weight function K(x) can be expressed

as a product of a bounded weight function tb(x) and Kc(x).


This approach will be referred to as the "two-point" mechanism in the remainder

of this section.

In the verification of I*-III*, the case r = 0 brings us back to the conditions

already verified for the null hypothesis case of Section 3.3. Only the case r = 1

remains. We start with condition I*a. The functions GN(x), N > 1, and G(x) are

continuous survival functions and


lim GN(x) = G(x); lim GN(x) = G(x) for all x.
N- -oo N-.oo







Due to a well-known result due to Polya (see e.g. Serfling (1980)), the uniform

convergence is proved. Condition I*b follows just as condition Ib did because K(x) =

d(x)K(x) where zt(x) is bounded.

To evaluate y(x) and other expressions, we need

dA~'(z)

gN(x)
GN(x)
rN(x)f(x : A) + (1 rN(x))f(x)
rN(x)F(x: A) + (1 rN(X))F(x)'

and

AN( dAo(x)
Aox) dx
f(x)
F(x)
= Ao(x).

Then
dhN(X)

dAo(x)

and

dAo(x) o(x)

7rN(x)f(: A) +(1 rN(x))f(x) F(x)
rN(x)F(x : A) + (1 rN(x))F(x) f (x)
rN(X) ( 1) + 1
((F(x:A 1) + 1"

Therefore -o(x) = 0, and 7(x) = -71(x). Now,

Y1(x) = lim NN -( 1)
N-.oo VNTo + N dAo(x)








lim ONNo + N (1
N-oo N N No + N dAo(x)
= No o1 7N *N /()-- F(S)_._]
= m 0+ oN 1 +
N--oo No + N No+N F+1)

Upon substituting 7N = -, we get

N0 (X) = hAm a F(x)
N-oo No +N N N1a VTrN ( ) i) +

S f(xA) F(x:)
= \/Pa ( f(X) F( x)j

= "Plpaw*(x)

as N -* oo, where w*(x) was defined at (3.4.6) in Theorem 3.4.2. This last con-

vergence is uniform on each closed subinterval of {x : F(x) > 0} by the same

reasoning (cf. (3.4.12), two-point mechanism) employed in Theorem 3.4.3. Likewise

as in (3.4.12),

i No + N I (x f(x : A) F(z : A) ( 'o(x)fl(x)
N--oo V-No f() F(x) I poo(x) + p- i(x) k(x

uniformly in probability on closed subintervals of 2*, with k(x) being left continuous

with right hand limits and k+(x) of bounded variation, again since 1b(x) is bounded

and the version of these properties for the log-rank statistic have been verified in

Gill (1980).

Condition II*a is the same as condition II in the null hypothesis case and thus is

already verified. Verification of conditions II*b and III* again makes use of the two-

point mechanism, along with Lemma 4.3.2 of Gill (1980) and his proof of Proposition

4.3.3. A pair of inequalities

K2 (x) Yo(x) Y(x) No + N, No + N, Yo(x)
Yi(x) No N Yo(x)+Y (x) N No




Full Text
xml version 1.0 encoding UTF-8
REPORT xmlns http:www.fcla.edudlsmddaitss xmlns:xsi http:www.w3.org2001XMLSchema-instance xsi:schemaLocation http:www.fcla.edudlsmddaitssdaitssReport.xsd
INGEST IEID E2FECQX96_YBCC07 INGEST_TIME 2017-07-13T21:54:11Z PACKAGE AA00003732_00001
AGREEMENT_INFO ACCOUNT UF PROJECT UFDC
FILES



PAGE 1

/,1($5 5$1. 7(676 )25 7+( 1215(6321'(56 352%/(0 :,7+ &(1625(' '$7$ %\ 9$6,/,6 %,// 3,.281,6 $ ',66(57$7,21 35(6(17(' 72 7+( *5$'8$7( 6&+22/ 2) 7+( 81,9(56,7< 2) )/25,'$ ,1 3$57,$/ )8/),//0(17 2) 7+( 5(48,5(0(176 )25 7+( '(*5(( 2) '2&725 2) 3+,/2623+< 81,9(56,7< 2) )/25,'$

PAGE 2

&RS\ULJKW k E\ 9DVLOLV %LOO 3LNRXQLV

PAGE 3

7R $OO 7KRVH :KR .HHS 7KHLU 'UHDPV $OLYH

PAGE 4

$&.12:/('*(0(176 PDNH QR DSRORJLHV IRU P\ LQGXOJHQFH LQ WKH IROORZLQJ VHQWHQFHV VLQFH P\ FRPSOHWLRQ RI WKLV GLVVHUWDWLRQ ZDV KHOSHG LQ VR PDQ\ ZD\V E\ VR PDQ\ SHRSOH )LUVW DQG IRUHPRVW WKDQN P\ SDUHQWV 6WDPDWLRV DQG (YDQJHOLD IRU WKHLU HYHUODVWLQJ ORYH DQG WKHLU WHDFKLQJV RI WKH WUHPHQGRXV YDOXHV WR EH JDLQHG IURP ZRUNLQJ KDUG DQG HDUQLQJ WKLQJV LQ OLIH 7KH UHVW RI P\ IDPLO\ DQG UHODWLYHV DOVR GHVHUYH WKDQNV WUXO\ DSSUHFLDWH WKH ZLVGRP RI 'U 39 5DR LQ KLV JXLGDQFH RI P\ 3K' SURn JUDP DP IRUWXQDWH IRU WKH HQWKXVLDVP RI VWDWLVWLFV VKDUHG ZLWK D KDQGIXO RI P\ IHOORZ VWXGHQWV ZKR KDYH EHFRPH YDOXHG FROOHDJXHV DQG IULHQGV HVSHFLDOO\ %HQ /DQJ DQG &DURO\Q +DQVHQ UHDGLO\ DFNQRZOHGJH DOO WKH 6WDWLVWLFV 'HSDUWPHQW IDFXOW\ LQ WKH PDLQ GLYLVLRQ WKDW KDYH LPSDUWHG WKHLU YDVW NQRZOHGJH RI VWDWLVWLFV WR PH VLQFH ZDV D HDJHU IUHVKPDQ DW WKH 8QLYHUVLW\ RI )ORULGD IHHO YHU\ OXFN\ ZLWK WKH LQYDOXDEOH H[SHULHQFH JDLQHG LQ P\ IRXU \HDUV DV D GDWD DQDO\VW DQG VWDn WLVWLFDO FRQVXOWDQW LQ WKH 'LYLVLRQ RI %LRVWDWLVWLFV GXH LQ ODUJH SDUW WR WKH VXSHUE SURIHVVLRQDOV WKDW VHUYH DV IDFXOW\ WKHUH ,Q SDUWLFXODU WKDQN 'U 0LFKDHO &RQ ,RQ DQG 0U 3KLO 3DGJHWW IRU WKHLU YLVLRQ DQG WKDQNOHVV VXSSRUW WKDW KDV OHG WR WKH ZRUNVWDWLRQ FRPSXWLQJ HQYLURQPHQW VR FUXFLDO WR WKLV PDQXVFULSW ,Q SDUWLFXODU WKH ZRQGHUIXO GRFXPHQW SUHSDUDWLRQ V\VWHP O$7J; /DPSRUW f DQG LWV JHQHVLV 7J; .QXWK f ZHUH XVHG WR W\SHVHW WKLV PDQXVFULSW 6SOXV %HFNHU &KDPEHUV DQG ,9

PAGE 5

:LONV 6WDWLVWLFDO 6FLHQFHV f SURGXFHG WKH JUDSKLFV DQG VLPXODWLRQV DQG 0DWKHPDWLFD :ROIUDP f SURYLGHG QXPHULFDO LQWHJUDWLRQV 'U 6FRWW (PHUVRQ GHVHUYHV WKDQNV IRU FRQVWDQW KHOS DQG QHYHU RQFH FRPSODLQLQJf LQ P\ HDUO\ GD\V RI WU\LQJ WR OHDUQ WKH ZRUNVWDWLRQ HQYLURQPHQW DP JUDWHIXO IRU P\ PDQ\ ORQJWLPH IULHQGV WKDW KDYH DOZD\V VXSSRUWHG PH DQG LQVSLUHG PH WR NHHS JRLQJ LQ WKRVH WLPHV RI LQHYLWDEOH YDOOH\V

PAGE 6

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

PAGE 7

8QFHQVRUHG 'DWD ([SHFWHG 6FRUHV &HQVRUHG 'DWD ([SHFWHG 6FRUHV &203$5$7,9( 678',(6 3LWPDQ $V\PSWRWLF 5HODWLYH (IILFLHQFLHV 6LPXODWLRQ 6WXG\ 5HDO 'DWD ([DPSOHV 6800$5< $1' &21&/86,216 5()(5(1&(6 %,2*5$3+,&$/ 6.(7&+ YLL

PAGE 8

/,67 2) 7$%/(6 7DEOH SDJH 3LWPDQ $5( IRU PLVVSHFLILHG $ PL[HG QRUPDO GLVWULEXWLRQ 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG QRUPDO GLVWULEXWLRQ 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG QRUPDO GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG QRUPDO GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK QR FHQVRULQJ 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK DEVHQFH RU SUHVHQFH RI H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HG PRGHO OLQHDU UDQN WHVW PL[HG H[WUHPHYDOXH GLVWULEXWLRQ ZLWK DEVHQFH RU SUHVHQFH RI H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI f (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI YLLL

PAGE 9

(PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI &KDQJH LQ SDLQ PHDVXUHV IURP GLDEHWLF QHXURSDWK\ VWXG\ &RPSDULVRQ RI WHVW VWDWLVWLF YDOXHV XQFHQVRUHG GDWD H[DPSOH 7HVW VWDWLVWLF YDOXHV DQG FRPSXWHG SYDOXHV XQFHQVRUHG GDWD H[DPSOH 6XUYLYDO WLPHV LQ GD\V IURP 9HWHUDQfV $GPLQLVWUDWLRQ OXQJ FDQFHU WULDO SDWLHQWV UHFHLYLQJ WHVW WKHUDS\ 3YDOXHV IRU 9$ OXQJ FDQFHU FHQVRUHG GDWD H[DPSOH ,;

PAGE 10

/,67 2) ),*85(6 7DEOH SDJH *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ UDQGRP REVHUYDWLRQV IURP D QRUPDO GLVWULEXWLRQ UDQGRP REVHUYDWLRQV IURP DQ H[WUHPHYDOXH GLVWULEXWLRQ *UDSK RI WHVW VWDWLVWLF EHKDYLRU XQFHQVRUHG GDWD H[DPSOH [

PAGE 11

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

PAGE 12

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

PAGE 13

&+$37(5 ,1752'8&7,21 7KH 1RQUHVSRQGHUV 3UREOHP 7KH ffQRQUHVSRQGHUVf SUREOHP PD\ DULVH LQ VWXGLHV GHVLJQHG WR HYDOXDWH WKH HIILFDF\ DQGRU WR[LFLW\ RI QHZ GUXJV 6XFK VWXGLHV JHQHUDWH GDWD IURP WZR JURXSVf§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f SUHVHQWV DQ H[FHOOHQW GLVFXVVLRQ RI WKH QRQUHVSRQGHUV SUREOHP +H QRWHV WKDW PDQ\ SURVSHFWLYH GUXJ FRPSRXQGV DUH GHVLJQHG WR FRPEDW D SDUWLFXODU FDXVH RI GLVHDVH WKDW FDQ EH VXFFHVVIXOO\ LGHQWLILHG DQG WDUJHWHG 2QH H[DPSOH FLWHG E\ 6DOVEXUJ f LV DQ HQ]\PHLQKLELWRU FRPSRXQG IRU HPSK\VHPD 6XFK D FRPSRXQG VKXWV GRZQ WKH DFWLYLW\ RI D SDUWLFXODU SURWHRO\WLF HQ]\PH WKDW LV NQRZQ WR EH D PDMRU IDFWRU LQ WKH SUHVHQFH RI WKH GLVHDVH 2WKHU SDWLHQWV ZLWK HPSK\VHPD PD\ QRW KDYH WKH HQ]\PH DV D SULPDU\ DJHQW VR WKDW WKH FRPSRXQG ZLOO FRQVHTXHQWO\ QRW DIIHFW WKH HPSK\VHPD

PAGE 14

,Q D VLPLODU YHLQ VHUXP DFWLYLW\ RI FHUWDLQ HQ]\PHV LQFUHDVH ZKHQ WKH GLVHDVH RI KHSDWLWLV LV SUHVHQW 0HGLFDO UHVHDUFKHUV PD\ WU\ WR LVRODWH WKH HQ]\PHVf DQG LQYHVWLJDWH ZKHWKHU D ORZHULQJ RI WKH VHUXP HQ]\PH OHYHOVf ZLOO UHVXOW LQ DPHOLRn UDWLRQ RI WKH KHSDWLWLV IRU SDWLHQWV :H PD\ EH DEOH RQO\ WR GHWHUPLQH D VSHFLILF HQ]\PH DV D PDMRU ULVN IDFWRU E\ WUHDWLQJ D SDWLHQW ZLWK D FRPSRXQG GHVLJQHG WR VSHFLILFDOO\ DFW RQ VHUXP HQ]\PH OHYHOV ,Q FDVHV ZKHUH WKH HQ]\PH LV WKH FDXVH RI WKH GLVHDVH WKH SDWLHQW ZLOO UHVSRQG LQ RWKHU FDVHV KHVKH ZLOO QRW 7KHUH LV QR H[WHUQDO PHFKDQLVP WR GHWHUPLQH ZKHWKHU RU QRW D SDWLHQW LV D UHVSRQGHU WR WKH WUHDWPHQW %HVLGHV HQ]\PHLQKLELWRUV 6DOVEXUJ f PHQWLRQV UHFHSWRU VLWH DJRQL]HUV DQG KRUPRQHPLPLFNHUV DV SURVSHFWLYH FRPSRXQGV WR FRPEDW FRQGLWLRQV VXFK DV FRQn JHVWLYH KHDUW IDLOXUH DQG DUWKULWLV &OLQLFDO LQYHVWLJDWLRQV RI VXFK FRPSRXQGV ZLOO HQFRXQWHU WKH VDPH QRQUHVSRQGHUV SUREOHP %RRV DQG %URZQLH f PHQWLRQ WKH DUHDV RI QXWULWLRQDO VXSSOHPHQWDWLRQ DQG EHKDYLRUDO WR[LFRORJ\ ZKHUH WKH DVn VXPSWLRQ RI WKH H[LVWHQFH RI QRQUHVSRQGHUV LV UHDVRQDEOH 7KH XVH RI DQWLELRWLFV RQ UDWV LQIHFWHG ZLWK WKH +HUSHV YLUXV VHUYHG DV DQ LOOXVWUDWLRQ RI WKH QRQUHVSRQGHUV SKHQRPHQRQ IRU *RRG f -RKQVRQ 9HULOO DQG 0RRUH f UHSRUWHG RQ D VWXG\ E\ &DUDQR DQG 0RRUH f LQ ZKLFK VXEMHFWWRVXEMHFW YDULDWLRQ RI FRPSOH[ ERG\ PHFKDQLVPV IRU GHDOn LQJ ZLWK PHGLFDWLRQV UHVXOWHG LQ RQO\ D VXEVHW RI VXEMHFWV UHDFWLQJ WR WUHDWPHQW &DUDQR DQG 0RRUH f ZHUH LQWHUHVWHG LQ VWXG\LQJ 6LVWHU &KURPDWLG ([FKDQJHV 6&(f DV DQ LQGLFDWRU RI FDUFLQRJHQLFLW\ LQ KXPDQ VPRNHUV $ ODUJHU IUHTXHQF\ RI

PAGE 15

KLJK 6&( YDOXHV SHU FHOO DSSHDUHG LQ PDQ\ VXEMHFWV ZKR ZHUH VPRNHUV EXW VXEMHFW WRVXEMHFW YDULDWLRQ ZDV KLJKO\ SUHYDOHQW DQG PDGH LW GLIILFXOW WR GHWHFW D GLIIHUHQFH LQ 6&( GLVWULEXWLRQV IRU VPRNHUV DQG QRQVPRNHUV 7KH GDPDJH LQ FHOOV ZDV GHn VFULEHG DV SHUVLVWHQW DOWKRXJK RQO\ RFFXULQJ LQ D VPDOO IUDFWLRQ RI WKHP 'DWD IRU D VLPLODU VLWXDWLRQ ZKHUH FKHPRWKHUDS\ LV D WR[LF VXEVWDQFH WKDW LV K\SRWKHVL]HG WR LQFUHDVH 6&( FRXQWV LQ VRPH FHOOV LV JLYHQ LQ WKH -RKQVRQ HW DO f DUWLFOH 7KH FRXQWV IRU D VDPSOH RI FHOOV IURP D SDWLHQW DUH PHDVXUHG EHIRUH XQGHUJRLQJ WKH WKHUDS\ DQG DJDLQ IRU D VHFRQG VDPSOH WDNHQ DIWHU DGPLQLVWUDWLRQ 7KH H[DPSOHV RI WKH QRQUHVSRQGHUV SKHQRPHQRQ GHVFULEHG WKXV IDU SDUWLFXODUO\ WKH ODVW RQH RI FKHPRWKHUDS\ LQYROYH GDWD WKDW DUH FRPSOHWHO\ REVHUYDEOH $ QDWn XUDO H[WHQVLRQ LV WKH VFHQDULR LQ ZKLFK VRPH RI WKH REVHUYDWLRQV DUH LQFRPSOHWH RU FHQVRUHG 7KLV LV D IHDWXUH IRU UHVSRQVHV RI WKH WLPHWRHYHQW QDWXUH VXFK DV WLPH WRUHODSVH WLPHWRGHDWK WLPHWRUHFXUUHQFH HWF $ VXEMHFWfV REVHUYDWLRQ PD\ RQO\ EH NQRZQ WR H[FHHG VRPH YDOXH ,Q PHGLFDO VWXGLHV WKLV DVSHFW RI FHQVRULQJ SURGXFHV ZKDW LV FDOOHG VXUYLYDO GDWD $ FOLQLFDO WULDO RI FDQFHU SDWLHQWV ZKR UHFHLYH RQH RI WZR WKHUDSLHV ZLOO LQYROYH GDWD RI WKH WLPHWRHYHQW QDWXUH ZLWK WKH IHDWXUH RI FHQVRULQJ 3DWLHQWV UHFHLYLQJ FRQYHQWLRQDO UDGLDWLRQ WKHUDS\ DUH FRQVLGHUHG WKH fFRQWUROVf ZKLOH RWKHU SDWLHQWV UHFHLYLQJ D FRPELQDWLRQ RI UDGLDWLRQ DQG FKHPRWKHUDS\ PDNH XS WKH WUHDWPHQW JURXS &RQFHLYDEO\ WKHUH PD\ EH SDWLHQWV ZKHUH WKH FKHPRWKHUDS\ KDV QR HIIHFW DQG WKRVH WUHDWHG QRQUHVSRQGHU SDWLHQWV ZLOO KDYH VXUYLYDO WLPHV OLNH WKH FRQWURO SDWLHQWV &OLQLFDO WULDOV LQYDULDEO\ SURGXFH SDWLHQWV VXUYLYLQJ DW WLPH RI DQDO\VLV

PAGE 16

RU SHUKDSV SDWLHQWV fORVW WR IROORZXSf E\ UHDVRQ RI PRYLQJ DZD\ RU GHDWK GXH WR D FDXVH XQUHODWHG WR WUHDWPHQW 6XFK SDWLHQWV ZLOO KDYH FHQVRUHG WLPHV 2WKHU PHGLFDO VWXGLHV DWWHPSW WR DVVHVV WKH HIIHFWV RI WUDQVSODQWHG RUJDQV RQ VXUYLYDO 7KH KXPDQ ERG\fV WHQGHQF\ WR UHMHFW IRUHLJQ WLVVXH PD\ UHQGHU WKH WUDQVn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n LQJ HTXDWLRQV ZLWKLQ VHFWLRQ 7DEOHV DQG ILJXUHV ZLOO EH QXPEHUHG ZLWKLQ FKDSWHU 7KHRUHPV &RUROODULHV DQG /HPPDV DUH FRXQWHG ZLWKLQ VHFWLRQ DQG DUH QXPEHUHG

PAGE 17

LQGHSHQGHQWO\ RI RQH DQRWKHU )RU H[DPSOH WKH ILUVW WKHRUHP LQ 6HFWLRQ LV 7KHRn UHP DQG WKH ILUVW OHPPD LQ 6HFWLRQ LV /HPPD 7KH VHFRQG UHIHUHQFHG HTXDWLRQ LQ WKDW VHFWLRQ LV f

PAGE 18

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n VSRQGHUV SUREOHP LV FRQWDLQHG LQ 6HFWLRQ 7KH 0L[WXUH 0RGHO /HW ; GHQRWH WKH UHVSRQVH YDULDEOH DVVRFLDWHG ZLWK PHPEHUV LQ WKH FRQWURO JURXS DQG OHW ;L GHQRWH WKH UHVSRQVH YDULDEOH IRU WKRVH VXEMHFWV LQ WKH WUHDWPHQW JURXS &DOO 5 WKH LQGLFDWRU YDULDEOH ZKLFK GHOLQHDWHV ZKHWKHU RU QRW D WUHDWHG VXEMHFW LV D UHVSRQGHU WKDW LV ^ LI WKH WUHDWHG VXEMHFW LV D UHVSRQGHU LI WKH WUHDWHG VXEMHFW LV D QRQUHVSRQGHU

PAGE 19

7KHQ WKH WUXH SURSRUWLRQ RI UHVSRQGHUV LQ WKH WUHDWHG SRSXODWLRQ LV JLYHQ E\ U 3U5 f f 7KH GLVWULEXWLRQ RI ;L WKH UHVSRQVH IRU D WUHDWHG VXEMHFW FDQ EH UHSUHVHQWHG DV D PL[WXUH RI WZR FRQGLWLRQDO GLVWULEXWLRQVf§RQH WKH GLVWULEXWLRQ RI WKH UHVSRQVH IRU D UHVSRQGHU VXEMHFW DQG WKH RWKHU WKH GLVWULEXWLRQ RI WKH UHVSRQVH IRU D QRQUHVSRQGHU VXEMHFW /HW WKH DVVRFLDWHG VXUYLYDO IXQFWLRQV IRU WKH WZR FRQGLWLRQDO GLVWULEXWLRQV EH GHQRWHG E\ )U[f 3U;L [ 5 f )15[f 3U$G [ 5 f UHVSHFWLYHO\ 7KHQ ZLWK Q DV LQ f *[f 3U$G [f 3U$G [ 5 f 3U5 f 3U$M [ 5 f 3UL" f [)U^[f WWf)MYN[f f LV WKH VXUYLYDO IXQFWLRQ DVVRFLDWHG ZLWK WKH GLVWULEXWLRQ RI ;? 7KH IROORZLQJ DVVXPSWLRQV DUH PDGH WKURXJKRXW WKH UHPDLQGHU RI WKLV GLVVHUWDn WLRQ $O 7KH GLVWULEXWLRQ RI WKH PHDVXUHG YDOXH IRU D VXEMHFW LQ WKH FRQWURO JURXS LV WKH VDPH DV WKH GLVWULEXWLRQ RI D PHDVXUHG YDOXH IRU D QRQUHVSRQGLQJ VXEMHFW LQ WKH WUHDWPHQW JURXS 7KDW LV )[f 3U$ [f )QU[f

PAGE 20

$ 7KH PHDVXUHG YDOXH IRU D UHVSRQGLQJ VXEMHFW LQ WKH WUHDWHG JURXS LV VWRFKDVWLFDOO\ ODUJHU WKDQ WKH PHDVXUHG YDOXH IRU D WUHDWHG QRQUHVSRQGHU 7KDW LV )U[f )15[f IRU DOO [ ZLWK VWULFW LQHTXDOLW\ IRU DW OHDVW RQH [ $ %RWK )U DQG )AU DUH PHPEHUV RI D IDPLO\ RI VXUYLYDO IXQFWLRQV LQGH[HG E\ D UHDO SDUDPHWHU $ ) ^)[ $f$RR` f ZKHUH )[ $f LV FRQWLQXRXV ZLWK GHQVLW\ I[ $f DQG LV VXFK WKDW )[ f )QU[f )[f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n WKH PHDVXUHG YDOXH IRU D UHVSRQGLQJ VXEMHFW LQ WKH WUHDWHG JURXS LV VWRFKDVWLFDOO\ VPDOOHU WKDQ WKH PHDVXUHG YDOXH IRU D WUHDWHG QRQUHVSRQn GHU 7KDW LV )U^[f )cYU[f IRU DOO [ ZLWK VWULFW LQHTXDOLW\ IRU DW OHDVW RQH [

PAGE 21

$VVXPSWLRQ $ DQG SDUWLFXODUO\ f ZKHQ XVHG LQ WKH PL[WXUH PRGHO DW f LPSOLHV WKDW WKH VXUYLYDO IXQFWLRQ IRU DQ H[SHULPHQWDO VXEMHFW KDV WKH IRUP *[ 7 $f W)[ $f f§ Qf)[f [ $RR f ZKHUH )[f )^[ f LV WKH VXUYLYDO IXQFWLRQ IRU WKH FRQWURO VXEMHFWV 7KH FRUUHVSRQGLQJ GHQVLW\ IXQFWLRQ LV JLYHQ E\ J[ 7 $f U[ $f f§ Uf[f U $RR f 7KH VXUYLYDO IXQFWLRQV DW f UHSUHVHQW D WZRSDUDPHWHU IDPLO\ RI PRGHOV IRU WKH WZRVDPSOH QRQUHVSRQGHUV SUREOHP ,Q WKLV IDPLO\ WKH FODLP WKDW fWKHUH LV D WUHDWPHQW HIIHFWf FDQ EH LQWHUSUHWHG DV WKH FODLP fD SRVLWLYH SURSRUWLRQ RI WUHDWHG VXEMHFWV DUH UHVSRQGHUVf 7KXV D WHVW RI WKH QXOO K\SRWKHVLV +R 1R WUHDWPHQW HIIHFW DJDLQVW WKH UHVHDUFK K\SRWKHVLV +D 7KHUH LV D WUHDWPHQW HIIHFW FDQ EH SHUIRUPHG E\ WHVWLQJ + 7 YV +D LU f $Q H[DPLQDWLRQ RI WKH QRQUHVSRQGHUV PRGHO DW f VKRZV WKDW WKH K\SRWKHVHV DW f DUH HTXLYDOHQW WR WKH K\SRWKHVHV + *[ 7 $f )[f YV +D *[ WW $f )[f f

PAGE 22

7KH UHVHDUFK K\SRWKHVLV DW f PHDQV WKDW ;L LV VWRFKDVWLFDOO\ ODUJHU WKDQ ;T 7KXV DQ\ WZRVDPSOH UDQN WHVW IRU VWRFKDVWLF RUGHULQJ VXFK DV WKH :LOFR[RQ UDQN VXP WHVW ZLOO SURYLGH D QRQSDUDPHWULF WHVW IRU WHVWLQJ +T YV +D +RZHYHU VLQFH WKHVH WHVWV GR QRW XVH WKH VSHFLILF IRUP RI *[f XQGHU +D LW LV QDWXUDO WR VHDUFK IRU WHVWV WKDW DUH PRUH HIILFLHQW IRU WHVWLQJ IRU WUHDWPHQW HIIHFWV XQGHU WKH PRGHO DW f )RU WKH FDVH ZKHUH WKHUH LV QR FHQVRULQJ RI WKH GDWD VHYHUDO DXWKRUV *RRG %RRV DQG %URZQLH -RKQVRQ HW DK &RQRYHU DQG 6DOVEXUJ f KDYH GHYHORSHG WHVWV RI + DVVXPLQJ RQH RI WKH IROORZLQJ IRUPV IRU )[ $f Lf /RFDWLRQ PRGHO LLf 6FDOH PRGHO LLLf /HKPDQQ PRGHO LYf /HKPDQQ PRGHO )[ f§ $f f§RR [ RR $ )[H$f [ $ >)[f@H f§RR [ RR $ f§ > f§ )[f@H f§RR [ RR $ 1RWH WKDW )[ $f LV DQ H[SOLFLW IXQFWLRQ RI )[f LQ WKH ODVW WZR FDVHV ,Q WKH FRQWH[W RI VXUYLYDO GDWD WKH PRGHO IRU VFDOH DOWHUQDWLYHV DSSHDUV PRUH DSSURSULDWH EHFDXVH VXUYLYDO WLPHV DUH QRQQHJDWLYH UDQGRP YDULDEOHV ZKRVH GLVn WULEXWLRQV DUH RIWHQ VNHZHG +RZHYHU VLQFH WKH QDWXUDO ORJDULWKP WUDQVIRUPDWLRQ 7[f ORJDf WUDQVIRUPV WKH VFDOH DOWHUQDWLYHV WR ORFDWLRQ DOWHUQDWLYHV UDQNEDVHG WHVWV IRU WKH FDVH RI D VFDOH PRGHO DUH LGHQWLFDO WR WKRVH IRU WKH ORFDWLRQVKLIW PRGHO XQGHU WKH ORJ WUDQVIRUPDWLRQ $FFRUGLQJO\ LQ WKH UHPDLQGHU RI WKLV ZRUN DWWHQWLRQ LV FRQILQHG WR ORFDWLRQ PRGHOV RQO\

PAGE 23

7KH PRGHOV LLLf DQG LYf KDYH EHHQ H[SORUHG E\ &RQRYHU DQG 6DOVEXUJ f 7KHLU PRGHOV DUH H[SUHVVHG LQ WHUPV RI FXPXODWLYH GLVWULEXWLRQ IXQFWLRQV ,QGHHG LI ZH DVVXPH RXU PRGHO LLLf WKHQ LW LV VWUDLJKWIRUZDUG WR VKRZ WKDW WKH FRUUHVSRQGLQJ FXPXODWLYH GLVWULEXWLRQ IXQFWLRQ LV f§ *; 7 $f 7 L >)rU m‘f> )Lf@ ZKLFK LV WKHLU f0RGHO f ,W VKRXOG DOVR EH QRWHG WKDW WKHLU SDUDPHWHU D LV UHODWHG WR $ WKURXJK WKH UHODWLRQVKLS D IRU D 6LPLODUO\ XQGHU PRGHO LYf *^[ 7 $f 7 > f§ )[f@H$ Uf > )[f@ FRUUHVSRQGV WR WKH &RQRYHU DQG 6DOVEXUJ f f0RGHO f $ *UDSKLFDO ([DPSOH &RQVLGHU WKH ORFDWLRQVKLIW PRGHO *[ 7 $f Q)[ f§ $f I f§ Wf)[f IRU f 9DOXHV RI U WKH WUXH SURSRUWLRQ RI UHVSRQGHUV LQ WKH WUHDWHG SRSXODWLRQ ZLOO LQIOXHQFH WKH VKDSH RI WKH GHQVLW\ LQ f J[ 7 $f UI[ $f Uf[f 7KH VKDSH RI J[ U $f ZLOO PDWFK WKH VKDSH RI WKH GHQVLW\ I[f IRU ; ZKHQ LU RU 7 7KH GHJUHH RI PRGLILFDWLRQ WR WKH GHQVLW\ VKDSH LQFUHDVHV DV WKH YDOXH RI $ WHQGV DZD\ IURP ]HUR DQGRU WKH YDOXH RI U WHQGV DZD\ IURP HLWKHU ]HUR RU RQH

PAGE 24

)RU WKH SXUSRVH RI LOOXVWUDWLRQ OHW XV FRQVLGHU WKH FDVH ZKHUH WKH UDQGRP YDULDEOH KDV WKH H[WUHPHYDOXH GLVWULEXWLRQ ZLWK GHQVLW\ I[ $f I[ f§ $f H[S f§[ f§ $f f§ 7KH VHULHV RI JUDSKV FRPSULVLQJ )LJXUHV LQGLFDWH KRZ WKH YDOXHV IRU U DQG $ GLFWDWH ULJKWWDLO EHKDYLRU IRU WKH GLVWULEXWLRQ RI ;? 7KH ORFDWLRQ VKLIW SDUDPHWHU $ LV ODEHOOHG 'HOWD LQ WKH IROORZLQJ JUDSKV 7KH SDUDPHWHU [ LV ODEHOOHG 3L :KHQ $ WKH VKDSHV RI WKH GLVWULEXWLRQV IRU ;? VROLG OLQH GHQVLW\ IRU WKH WUHDWPHQW SRSXODWLRQf DQG ;T GRWWHG OLQH GHQVLW\ IRU WKH FRQWURO SRSXODWLRQf UHPDLQ TXLWH VLPLODU IRU WKH UDQJH RI YDOXHV RI [ 'LIIHUHQFHV LQ WKH GHQVLWLHV RQO\ EHFRPH DSSDUHQW IRU YDOXHV RI [ ,Q FRPSDULVRQ D GLVWLQFWLRQ EHWZHHQ WKH GHQVLWLHV RI ; DQG ;? ZKHQ $ FDQ EH VHHQ DV HDUO\ DV IRU WKH YDOXH [ 7KH VKDSH IRU WKH GHQVLW\ DVVRFLDWHG ZLWK ;? fIODWWHQV RXWf DW DURXQG [ DQG fUHFRYHUVf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n VWUXFWLRQ RI D OLNHOLKRRG IRU WKH GDWD )RU H[DPSOH UHIHU WR .DOEIOHLVFK DQG 3UHQWLFH

PAGE 25

38 38 ([WUHPH9DOXH 'HOWD 3L )LJXUH *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ 7UHDWPHQW GHQVLW\ J[ Wf &RQWURO GHQVLW\ I[f

PAGE 26

38 38 ([WUHPH9DOXH 'HOWDr 3L )LJXUH *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ 7UHDWPHQW GHQVLW\ J[ U f &RQWURO GHQVLW\ I[f

PAGE 27

38 38 ([WUHPH9DOXH 'HOWD 3L )LJXUH *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ 7UHDWPHQW GHQVLW\ J[ Wf &RQWURO GHQVLW\ I[f

PAGE 28

3L 3L ([WUHPH9DOXH 'HOWD 3L )LJXUH *UDSK RI H[WUHPHYDOXH PL[WXUH PRGHO $ 7UHDWPHQW GHQVLW\ J[ Wf &RQWURO GHQVLW\ I[f

PAGE 29

&K f IRU D VXUYH\ DQG GLVFXVVLRQ RI WKH GLIIHUHQW FHQVRULQJ W\SHV DQG WKHLU DSSURSULDWHQHVVf 7KHUH DUH 1 VXEMHFWV XQGHU VWXG\ RI ZKLFK 1R DUH LQ WKH FRQWURO JURXS DQG 1L DUH LQ WKH WUHDWPHQW JURXS /HW U IRU WKH FRQWURO JURXS DQG U IRU WKH WUHDWPHQW JURXS $VVRFLDWHG ZLWK WKH WK VXEMHFW LQ WKH UWK JURXS DUH WZR UDQGRP YDULDEOHV ;UW WKH SRWHQWLDO IDLOXUH WLPH IRU WKH ]WK VXEMHFW LQ JURXS U &7; WKH SRWHQWLDO FHQVRULQJ WLPH IRU WKH WK VXEMHFW LQ JURXS U )RU WKH ]WK VXEMHFW LQ JURXS U ZH REVHUYH WKH YDOXHV RI WKH UDQGRP YDULDEOH $U W f§ PLQ$UUO &Uf DQG LI ;UL ;UL@ 67L LI ;UL f§ &UL 7KXV 6UL WDNHV RQ WKH YDOXH LI WKH REVHUYDWLRQ IRU VXEMHFW L LQ JURXS U LV QRW FHQVRUHG DQG RWKHUZLVH 8QGHU WKH UDQGRP FHQVRUVKLS PRGHO ZH DVVXPH f $nRA&RLf ;RQ&RQf $ILA&Qf DUH PXWXDOO\ LQn GHSHQGHQW SDLUV f ;UL DQG &UW DUH LQGHSHQGHQW DQG FRQWLQXRXV ZLWK VXUYLYDO IXQFWLRQV *[ 7 $f DQG /[f UHVSHFWLYHO\ f 7KH IRUP RI /[f GRHV QRW GHSHQG XSRQ U RU $

PAGE 30

7KH WKUHH DVVXPSWLRQV RI UDQGRP FHQVRUVKLS LPSOLHV D QRQLQIRUPDWLYH VWUXFWXUH DERXW WKH FHQVRULQJ PHFKDQLVP 0RVW RI WKH UHVXOWV LQ WKH VWDWLVWLFDO OLWHUDWXUH DUH GHYHORSHG XQGHU WKHVH DVVXPSWLRQV 2QH IHDWXUH RI WKH QRQLQIRUPDWLYH VWUXFWXUH LV DQ RSSRUWXQLW\ WR FRQVWUXFW D SDUWLDO OLNHOLKRRG IRU WKH REVHUYHG GDWD 2WKHU 1RWDWLRQV :KHQ LW LV QHFHVVDU\ WR XVH WKH UDQGRP YDULDEOH DVVRFLDWHG ZLWK WKH VXUYLYDO IXQFWLRQ )[f WKH QRWDWLRQ RI HLWKHU ) RU );f ZLOO EH HPSOR\HG LQ WKLV GLVVHUWDWLRQ 7KLV FRQYHQWLRQ DSSOLHV WR RWKHU UDQGRP YDULDEOHV DV ZHOO $ IL[HG RU UDQGRPf IXQFWLRQ WKDW WDNHV RQ WKH YDOXHV )[f DW WKH SRLQW [ PD\ EH GHQRWHG E\ HLWKHU )f RU ) 7KH QRWDWLRQ )U[f *^[f f /^[f "U;UL [f LV IRU WKH VXUYLYDO IXQFWLRQ RI ;7^ $OVR $[f J[f *[f GHQRWHV WKH KD]DUG IXQFWLRQ DW WLPH [ DQG $[f I $VfGV -R GHQRWHV WKH FXPXODWLYH KD]DUG IXQFWLRQ DW WLPH [ 7KH LQWHJUDO RI D IXQFWLRQ VXFK DV $Vf ZLWK UHVSHFW WR WKH YDULDWLRQ RI V RYHU VRPH LQWHUYDO LQ WKH UHDO OLQHf ZLOO EH GHQRWHG DV LQ

PAGE 31

7KLV ODVW LQWHJUDO FRXOG DOVR EH UHSUHVHQWHG DV D /HEHVJXH6WLHOWMHV LQWHJUDO ZLWK UHVSHFW WR WKH WRWDO YDULDWLRQ RI $[f VXFK DV LQ (VWLPDWHV IURP WKH GDWD RI VXFK TXDQWLWLHV ZLOO EH GHQRWHG XVLQJ WKH fKDWf QRWDWLRQ HJ )[f LV VRPH UHDVRQDEOH HVWLPDWH RI )[f 5HDOL]DWLRQV RI ;UW DUH GHQRWHG E\ [U ZKHWKHU FHQVRULQJ RFFXUV RU QRW 1RZ VXSn SRVH WKDW ZH ZLVK WR UHIHU WR DOO WKH REVHUYDWLRQV LUUHVSHFWLYH RI JURXS PHPEHUVKLS 'URSSLQJ WKH VXEVFULSW U IURP [UW SURGXFHV ;? ;SM DV WKH REVHUYHG WLPHV IRU WKH 1 VXEMHFWV LQ WKH FRPELQHG VDPSOH /HW N -ELf GHQRWH WKH QXPEHU RI GLVWLQFW XQFHQVRUHG WLPHV LQ WKH FRQWURO WUHDWPHQWf VDPSOH DQG VHW N N N? /HW ;f ;Of ;f f f f ;Nf ;IFLf UHSUHVHQW WKH RUGHUHG XQFHQVRUHG WLPHV LQ WKH FRPELQHG VDPSOH :LWKLQ WKH LQWHUYDO ;Mf L VXSSRVH WKDW WKHUH DUH P WRWDO FHQVRUHG REVHUYDWLRQV f f f 7LfPn 'HILQH ^ LI ;Mf FRUUHVSRQGV WR D WUHDWHG VXEMHFW RWKHUZLVH 7KXV =Wf LV WKH JURXS PHPEHUVKLS LQGLFDWRU FRUUHVSRQGLQJ WR ;S 7KH FHQVRUHG YDOXHV ;Lf ZLWK e DQDORJRXVO\ KDYH WKH FRYDULDWHV WR LQGLFDWH

PAGE 32

WKHLU JURXS PHPEHUVKLSV /HW PL 0L f§ A =Wf] L 7KHQ 0L LV WKH QXPEHU RI FHQVRULQJ WLPHV EHORQJLQJ WR WKH WUHDWPHQW JURXS LQ WKH LQWHUYDO >DTT ;Lff 6R P f§ 0 LV WKH QXPEHU RI FHQVRUHG REVHUYDWLRQV LQ WKH FRQWURO JURXS WKDW UHVLGH LQ >[T ;ff 7KH TXDQWLW\ N 5L f M L ZLOO EH FDOOHG fWKH VL]H RI WKH ULVN VHW DW WLPH ;ff DQG LV WKH QXPEHU RI VXEMHFWV ZKRVH YDOXHV DUH NQRZQ WR EH DW OHDVW ;f 7KH TXDQWLWLHV DQG 5L GR QRW KDYH LQGLFHV LQ SDUHQWKHVHV VLQFH WKH\ DUH H[DPSOHV RI IXQFWLRQV RI WKH ;M 1RWH WKDW =M GRHV QRW IROORZ WKLV FRQYHQWLRQ /LWHUDWXUH 5HYLHZ 6XEUDKPDQLDQ 6XEUDKPDQLDQ DQG 0HVVHUL f QRWHG WKDW WKH XVH RI WKH LQGHSHQGHQW VDPSOH 6WXGHQWfV WWHVW ZLOO VXIIHU IURP UHGXFHG SRZHU ZKHQ WKH DOWHUn QDWLYH K\SRWKHVLV VSHFLILHV D PL[WXUH RI QRUPDO GLVWULEXWLRQV *RRG f DSSHDUV WR EH WKH ILUVW WR LQWURGXFH WKH PL[WXUH PRGHO WR DFFRXQW IRU WKH H[LVWHQFH RI QRQn UHVSRQGHUV LQ WKH WUHDWPHQW JURXS 7R DFFRXQW IRU WKH IDFW WKDW WKH SUHVHQFH RI QRQUHVSRQGHUV ZLOO GHFUHDVH WKH GLIIHUHQFH EHWZHHQ WKH PHDQV RI WKH WZR JURXSV DQG LQFUHDVH WKH YDULDQFH RI WKH WUHDWPHQW JURXS *RRG f SURSRVHG D QHZ UDQGRPL]DWLRQ WHVW EDVHG RQ WKH VWDWLVWLF [ ?;L;R r / L L f-9 f6f

PAGE 33

ZKHUH ƒR $Mf LV WKH VDPSOH PHDQ IRU WKH FRQWURO WUHDWPHQWf JURXS DQG 6M LV WKH XVXDO VDPSOH YDULDQFH IRU WKH WUHDWPHQW JURXS 1RWLFH WKDW WKH WHVW VWDWLVWLF LV D ZHLJKWHG VXP RI IXQFWLRQV LQYROYLQJ WKH GLIIHUHQFH LQ JURXS PHDQV DQG WKH YDULDQFH IRU WKH WUHDWPHQW JURXS 7KH FKRLFH RI E\ *RRG f DV WKH ZHLJKW ZDV PDGH LQ KRSHV RI ZLGH DSSOLFDELOLW\ RI WKH WHVW RYHU WKH XQNQRZQ UDQJH RI YDOXHV IRU LU DQG $ 2WKHU ZHLJKWV ZLWKLQ WKH LQWHUYDO >@ FRXOG EH XVHGf§D ZHLJKW RI JLYHV )LVKHUfV UDQGRPL]DWLRQ WWHVW 7KH HPSLULFDO SRZHU LQYHVWLJDWLRQV RI *RRG 7DEOH f GHWHUPLQHG WKDW WKH WHVW EDVHG RQ Af LQ f SHUIRUPHG PDUNHGO\ EHWWHU RYHU WKH UDQJH RI YDOXHV U e @ WKDQ 6WXGHQWfV WWHVW IRU VDPSOH VL]HV XQGHU WHQ ZKHQ )[ $f UHSUHVHQWHG WKH VWDQGDUG QRUPDO GLVWULEXWLRQ DQG $ RU ,W DOVR EHDW RXW )LVKHUfV UDQGRPL]DWLRQ WWHVW RYHU WKH HQWLUH UDQJH U e @ ZKHQ WKH XQGHUO\LQJ GLVWULEXWLRQV ZHUH ORJQRUPDO $SSOLFDWLRQV RI WKH WHVW EDVHG RQ Lf LQ f VKRZHG LWV HYLGHQFH RI LQFUHDVHG fVHQVLWLYLW\f *RRG f UHODWLYH WR 6WXGHQWfV W IRU UHDO GDWD WKDW H[KLELW WKH QRQUHVSRQGHUV VLWXDWLRQ 3UHVXPDEO\ WKH H[LVWHQFH RI JUHDWHU YDULDELOLW\ LQ DGGLWLRQ WR D VKLIW LQ ORFDWLRQ IRU WKH WUHDWPHQW JURXS UHVSRQVHV PDGH WKH WHVW EDVHG RQ f EHWWHU VXLWHG WKDQ WKH WWHVW IRU UHMHFWLQJ WKH QXOO K\SRWKHVLV RI fQR WUHDWPHQW HIIHFWf %RRV DQG %URZQLH f DGGUHVVHG VRPH LQWHUHVWLQJ TXHVWLRQV UDLVHG E\ *RRGfV f SDSHU 7KH LQWHUSUHWDWLRQ RI D VLJQLILFDQW SYDOXH ZDV RQH LVVXH %RRV DQG %URZQLH f HPSKDVL]HG WKDW DFFHSWDQFH RI WKH DOWHUQDWLYH K\SRWKHVLV GRHV QRW QHFHVVDULO\ LPSO\ D VKLIW LQ PHDQ $Q LQFUHDVH LQ WKH YDULDELOLW\ FRXOG EH VROHO\

PAGE 34

UHVSRQVLEOH 7KH JUDSKV LQ )LJXUH LQGLFDWH KRZ D VPDOO W YDOXH DQG D ODUJH $ YDOXH SURGXFHV PRUH YDULDELOLW\ LQ WKH WUHDWPHQW JURXS GLVWULEXWLRQ DOWKRXJK WKH PHDQV RI WKH WZR JURXSV DUH VLPLODU ,Q DGGLWLRQ WR FRUUHFWLQJ WKH SURFHGXUH IRU LPSOHPHQWLQJ D RQHVLGHG WHVW ZLWK f %RRV DQG %URZQLH f XVHG 0RQWH &DUOR VWXG\ UHVXOWV WR DUJXH WKDW 6WXGHQWfV WWHVW DQG WKH :LOFR[RQ UDQN VXP WHVW DUH DW OHDVW DV SRZHUIXO DV WKH WHVW EDVHG RQ f ZKHQ WKH XQGHUO\LQJ GLVWULEXWLRQV ZHUH QRUPDO RU H[WUHPHYDOXH DQG U 7KH DGYDQWDJH RI f DSSHDUHG DV $ LQFUHDVHG DQG Q ZDV OHVV WKDQ *URXS VDPSOH VL]HV RI HLJKW ZHUH XVHG $ VWXG\ ZLWK JURXS VDPSOH VL]HV RI WZHQW\ GLG QRW LQFOXGH f %RRV DQG %URZQLH f MXVWLILHG LWV RPLVVLRQ ZLWK D VWDWHPHQW E\ *RRG f RI GLPLQLVKHG HIIHFWLYHQHVV RI f DV 1R DQG 1L JUHZ ODUJHU 7KH QRQWHFKQLFDO DUWLFOH E\ 6DOVEXUJ f ZKLFK GLVFXVVHG VHYHUDO DSSOLFDn WLRQV RI WKH QRQUHVSRQGHU SKHQRPHQRQ LQGLFDWHV WKDW DQ LQWHUSUHWDWLRQ RI VRPH FKDQJH LQ WKH WUHDWPHQW JURXS ZKHWKHU LW EH SULPDULO\ GXH WR YDULDELOLW\ RU VKLIW LQ PHDQ LV XVHIXO LQ SUHOLPLQDU\ LQYHVWLJDWLRQV RI QHZ FOLQLFDO FRPSRXQGV 7KH VDPSOH VL]HV LQ VXFK VWXGLHV DUH XVXDOO\ VPDOO VR WKDW WKH SUHVHQFH RI QRQUHVSRQGHUV ZLOO GHFUHDVH SRZHU RI WHVWV VXFK DV 6WXGHQWfV W DQG WKH :LOFR[RQ 7KH XVH RI /HKPDQQ DOWHUQDWLYHV LQ WKH PL[WXUH PRGHO IRU WKH WUHDWPHQW JURXS ZDV SURSRVHG LQ D VXEVHTXHQW DUWLFOH DXWKRUHG E\ &RQRYHU DQG 6DOVEXUJ f 8Qn OLNH WKH DUWLFOHV RI *RRG f DQG %RRV DQG %URZQLH f D IRUPDO PHFKDQLVP WR GHULYH WHVWV VHQVLWLYH WR WKH DOWHUQDWLYH K\SRWKHVLV ZDV XVHG 7KH PHFKDQLVP ZDV &RQRYHUfV f WHFKQLTXH IRU GHULYLQJ D ORFDOO\ PRVW SRZHUIXO UDQN WHVW /0357f

PAGE 35

XQGHU PRUH JHQHUDO PRGHOV WKDQ WKH XVXDO ORFDWLRQVKLIW RU VFDOH FKDQJH VHWWLQJV 7KH /0357 LV D OLQHDU UDQN WHVW WKDW LV D VXP RI H[SHFWHG RU DSSUR[LPDWH VFRUHV VSHFLILFDOO\ JHQHUDWHG IURP WKH JLYHQ PRGHO DQG DVVLJQHG WR WKH REVHUYDWLRQV 5HFDOO WKDW WKH PL[WXUH PRGHO f KDV WZR SDUDPHWHUV U DQG $ &RQRYHU DQG 6DOVEXUJ f WRRN WKH DSSURDFK RI IL[LQJ RQH RI WKH SDUDPHWHUV DQG GHULYLQJ WKH /0357 VFRUHV IRU WKH RWKHU ,Q ERWK FDVHV WKH VFRUH IXQFWLRQV ZHUH LQGHSHQGHQW RI 7 6LQFH ERWK LU DQG $ LQGLFDWH HIIHFW GXH WR WUHDWPHQW LQ WKH PRGHO DW f &RQRYHU DQG 6DOVEXUJ f ZHUH LQWHUHVWHG LQ D ORVV RI SRZHU WKDW ZRXOG DULVH LQ XVLQJ RQH VFRUH IXQFWLRQ ZKHQ WKH RWKHU VFRUH IXQFWLRQ ZDV PRUH DSSURSULDWH $ FRPSDULVRQ RI WKH WZR VFRUH IXQFWLRQV LQ WHUPV RI 3LWPDQ DV\PSWRWLF UHODWLYH HIILFLHQF\ $5(f OHQW FUHHGHQFH WR D FRPSURPLVH VFRUH IXQFWLRQ EDVHG RQ D YDOXH RI $ WKDW PD[LPL]HG WKH 3LWPDQ $5( 7HVW VWDWLVWLFV EDVHG RQ WKH VFRUHV GHYHORSHG E\ &RQRYHU DQG 6DOVEXUJ f ZHUH VKRZQ WR EH DV\PSWRWLFDOO\ QRUPDO LQ GLVWULEXWLRQ )RU VPDOOHU VDPSOHV &RQRYHU DQG 6DOVEXUJ f VXJJHVW WKH XVH RI WKH WZRVDPSOH 6WXGHQWfV WWHVW FRPSXWHG RQ WKH VFRUHV 0RQWH &DUOR VWXGLHV LQGLFDWHG WKDW WKH HPSLULFDO VLJQLIn LFDQFH OHYHOV IRU WKH WHVWV ZHUH FORVH WR WKH FKRVHQ QRPLQDO VLJQLILFDQFH OHYHO IRU VDPSOH VL]HV DV IHZ DV ILYH LQ HDFK RI WKH JURXSV ZKHQ WKH WWHVW DSSUR[LPDWLRQ ZDV HPSOR\HG $SSO\LQJ WKH WHVWV RQ WZR H[DPSOHV RI UHDO GDWD LQGLFDWHV EHWWHU SHUIRUn PDQFH WKDQ 6WXGHQWfV W WKH :LOFR[RQ DQG *RRGfV WHVW EDVHG RQ f LQ WKH VHQVH RI FDOFXODWHG SYDOXHV 2QH H[DPSOH ZKLFK FRPSDUHV SDLQ YDOXHV IRU FRQWURO DQG WUHDWHG SDWLHQWV XQGHUJRLQJ DFXWH SDLQIXO GLDEHWLF QHXURSDWK\ KDG VDPSOH VL]HV RI

PAGE 36

1 $K 7KH RWKHU H[DPSOH RI 6*27 OLYHU IXQFWLRQ YDOXHV IRU KHDUW SDWLHQWV KDG VDPSOHV VL]HV RI 1R DQG 1? $ VLPLODU IRUPDO DSSURDFK RI UDQNV ZDV WDNHQ E\ -RKQVRQ HW DO f ZKHUH D ORFDWLRQVKLIW ZDV SRVWXODWHG IRU )[ $f -RKQVRQ HW DO f FOHDUO\ VWDWHG WKH WHVWLQJ SUREOHP WR EH WKH RQH FRQVLGHUHG LQ WKLV PDQXVFULSW DW f + 7 YV +D WW 7KH OLQHDU UDQN WHVWV GHULYHG E\ -RKQVRQ HW DO f ZHUH QRWHG WR EH EDVHG RQ VFRUH IXQFWLRQV WKDW DFFHQWXDWHG ODUJH UHVSRQVHV ZKLFK LV FRQWUDU\ WR WKH XVXDO DVSHFW RI VFRUH IXQFWLRQV IRU UDQN WHVWV VXFK DV WKH :LOFR[RQ 7KH H[DPSOH LQ &KDSWHU 2QH RI WKLV PDQXVFULSW WKDW UHIHUUHG WR KLJKHU 6&( FRXQWV IRU SDWLHQWV UHFHLYLQJ FKHPRWKHUDS\ VHUYHG DV DQ LOOXVWUDWLRQ RI WKH XVHIXOQHVV RI WKH WHVWV GHULYHG E\ -RKQVRQ HW DO f ,Q DV\PSWRWLF UHODWLYH HIILFLHQFLHV DQG 0RQWH &DUOR VWXGLHV WKH GHULYHG WHVWV SHUIRUPHG EHWWHU WKDQ VWDQGDUG WHVWV VXFK DV WKH :LOFR[RQ IRU D EURDG UDQJH RI FRQILJXUDWLRQV WKDW UHIOHFW WKH QRQUHVSRQGHUV SUREOHP 7ZR XQGHUO\LQJ IRUPV IRU )[ $f ZHUH FRQVLGHUHGf§XQLIRUP DQG QRUPDO 7KH QRUPDO GLVWULEXWLRQ ZLWK D ORFDWLRQ VKLIW JHQHUDWHG D VFRUH IXQFWLRQ WKDW ZDV GHn SHQGHQW RQ $ 7KH UHVXOWLQJ OLQHDU UDQN WHVW FRXOG WKHQ EH XVHG WR JHW DQ H[DFW FRQGLWLRQDO GLVWULEXWLRQ XQGHU WKH QXOO K\SRWKHVLV $V WKH VDPSOH VL]HV 1R DQG 1? LQFUHDVH FRPSXWDWLRQV EHFRPH SURKLELWLYH DQG DQ DV\PSWRWLF GLVWULEXWLRQ LV FRQYHQLHQW $OVR WKH VFRUH IXQFWLRQV PD\ QRW KDYH WUDFWDEOH H[SHFWDWLRQV VR WKDW

PAGE 37

DSSUR[LPDWH VFRUHV WKDW DUH DV\PSWRWLFDOO\ HTXLYDOHQW DUH XVHIXO 5HVXOWV IRU GHDOLQJ ZLWK WKHVH SUREOHPV DQG RWKHUV DUH V\VWHPDWLFDOO\ GHDOW ZLWK LQ WKH -RKQVRQ HW DO f DUWLFOH 7KH IROORZLQJ VXEVHFWLRQ VXPPDUL]HV WKHLU ILQGLQJV 3URSHUWLHV RI 8QFHQVRUHG 'DWD /LQHDU 5DQN 7HVWV 8QGHU WKH PL[WXUH PRGHO DW f WKH VFRUH IXQFWLRQ DVVLJQHG WR ;M LV ZKHUH 8L O )[f f )[ff DQG f ,Dff 7KH IXQFWLRQ f ZLOO EH VXEVHTXHQWO\ GHVLJQDWHG WKH fPL[HGPRGHOf VFRUH IXQFn WLRQ 7KH IRUP RI WKH VWDWLVWLF IRU WKH /0357 IRU WHVWLQJ + Q YV +D U LV 1 7a f Wn O ZLWK WKH H[SHFWDWLRQ 6 WDNHQ RYHU WKH MRLQW GHQVLW\ RI WKH RUGHU VWDWLVWLFV RI D UDQGRP VDPSOH RI VL]H 1 IURP D XQLIRUP f GLVWULEXWLRQ 7KH IDFW WKDW WKH ]WK RUGHU VWDWLVWLF IURP D XQLIRUP f GLVWULEXWLRQ KDV D EHWD GLVWULEXWLRQ ZLWK GHQVLW\ $+  f§ f 79 f§ f LL 8^ FDQ EH XWLOL]HG WR HYDOXDWH 7 XQGHU VSHFLILF IRUPV IRU M! VXFK DV ZKHQ WKH XQGHUO\LQJ GLVWULEXWLRQV )[ f§ $f $ DUH QRUPDO

PAGE 38

([DFW VLJQLILFDQFH OHYHOV DVVRFLDWHG ZLWK 7 DW f FDQ WKHQ EH FDOFXODWHG YLD WKH SHUPXWDWLRQ SULQFLSOH 7KH VFRUH IXQFWLRQ f FDQ DOVR EH XVHG ZLWK WKH DSSUR[LPDWLRQ e^W!^XLff Z W!>e^XLf? I! 1Ma WR JHW D VWDWLVWLF Wf f WKDW LV DV\PSWRWLFDOO\ HTXLYDOHQW WR 7 DW f 7KH DSSUR[LPDWH VFRUHV QRW RQO\ KDYH HDVLHU FRPSXWDWLRQDO IRUPV EXW DOVR SRVVHVV FORVHGIRUP H[SUHVVLRQV IRU PRVW RI WKH FRPPRQ GLVWULEXWLRQV 6LQFH FRPSXWDWLRQV ZLWK DOO SRVVLEOH SHUPXWDWLRQV FDQ TXLFNO\ EHFRPH WRR LQn WHQVLYH DV 1 LQFUHDVHV DV\PSWRWLF UHVXOWV DUH HPSOR\HG IRU DVVHVVLQJ VLJQLILFDQFH OHYHOV ZKHQ 1 LV ODUJH 8QGHU PLOG UHJXODULW\ FRQGLWLRQV VWDQGDUGL]HG YHUVLRQV RI ERWK f DQG f ZLOO EH DV\PSWRWLFDOO\ QRUPDOO\ GLVWULEXWHG XQGHU WKH QXOO K\SRWKHVLV 7+(25(0 $VVXPH WKDW Lf !^Xf DV GHILQHG E\ f LV PRQRWRQLF L LLf I W!XfGX RR ,I 9 LV HLWKHU f RU f WKHQ XQGHU WKH QXOO K\SRWKHVLV + LU Y

PAGE 39

ZKHUH 9DUWf 1T1? U > MfXfGX L -R 1 1O FRQYHUJHV LQ GLVWULEXWLRQ WR D VWDQGDUG QRUPDO UDQGRP YDULDEOH DV PLQ9R1Lf RR 3URRI 6HH -RKQVRQ HW DO f 7KHRUHP Â’ %HKDYLRU RI WKH VWDWLVWLFV 7 DW f DQG 7r DW f XQGHU DOWHUQDWLYH K\n SRWKHVHV KDV EHHQ KDQGOHG LQ WKH FRQWH[W RI VHTXHQFHV RI ORFDO SDUDPHWHU YDOXHV -RKQVRQ HW DO f SURYLGH IRUPDO GHWDLOV LQ WKH DSSHQGL[ RI WKHLU DUWLFOH 7KH GLVWULEXWLRQV RI 7 DQG 7r XQGHU VHTXHQFHV RI ORFDO DOWHUQDWLYH K\SRWKHVHV DUH DV\PSn WRWLFDOO\ QRUPDO DQG FDQ EH XVHG WR REWDLQ HIILFLHQF\ H[SUHVVLRQV $V PHQWLRQHG EHIRUH LQ UHYLHZ RI WKH &RQRYHU DQG 6DOVEXUJ f DUWLFOH WKH 3LWPDQ $5( FDQ EH XVHG WR KHOS GHWHUPLQH D YDOXH IRU $ LQ RUGHU WR FRQGXFW WKH WHVW /HW D EH VRPH FRQVWDQW 8QGHU D OLPLWLQJ VHTXHQFH RI ORFDO DOWHUQDWLYHV // \ PLQAR1Lf RR f WKH 3LWPDQ $5( FDQ EH FRPSXWHG WR H[SORUH ORVV RI HIILFLHQF\ IRU D SDUWLFXODU /0 357 GXH WR LQDFFXUDWH VSHFLILFDWLRQV VXFK DV WKH YDOXH RI $ 6LQFH WKH WHVW VWDWLVWLFV GHSHQG RQ $ D FKRLFH RI VRPH YDOXH WR VXEVWLWXWH IRU D XQNQRZQ SDUDPHWHU LV DQ LPSRUWDQW LVVXH 7KLV VHFWLRQ LQWURGXFHV VRPH HYLGHQFH RI WKH SUREOHP )XUWKHU VWXG\ LQ KRSHV RI ILQGLQJ DGHTXDWH VROXWLRQV LV GLVFXVVHG LQ ODWHU FKDSWHUV DIWHU WKH FHQVRUHG GDWD FDVH LV FRQVLGHUHG

PAGE 40

6XSSRVH M!FKXf GHQRWHV WKH FKRVHQ VFRUH IXQFWLRQ WR EH XVHG ZKLOH I!W^Xf GHQRWHV WKH VFRUH IXQFWLRQ ZKLFK FRQWDLQV WKH WUXH YDOXH RI $ 7KDW LV OHW 0Xf &XfA +)nOXff DQG 0 8! +)PX: Bf )+ ,,ff ZKHUH $F LV WKH FKRVHQ YDOXH RI $ DQG $W LV WKH WUXH YDOXH RI $ 7+(25(0 8QGHU WKH FRQGLWLRQV RI 7KHRUHP DQG f WKH 3LWPDQ $5( RI WKH WHVW VWDWLVWLF Y EDVHG RQ I!FK^Xf UHODWLYH WR M!WXf LV n L I!FKXf08fGX I I!FKXfGX I c!WXfGX HII$FL $Wf M\ 3URRI 6HH -RKQVRQ HW DO f 7KHRUHP ’ 7KH FRPSXWDWLRQ RI D 3LWPDQ $5( PD\ EH VLPSOLILHG ZLWK WKH QH[W UHVXOW /(00$ )RU WKH PL[HGPRGHO XQFHQVRUHG VFRUH IXQFWLRQ I!^XfGX RU HTXLYDOHQWO\ , I)O f§mf f§$f GX )LOXff 3URRI 7KH LQWHJUDWLRQ VXEVWLWXWLRQ [ ) f§ Xf SURGXFHV 9aY I[ $f M!XfGX I[fG[ ’

PAGE 41

&URVV SURGXFW WHUPV WKDW DULVH ZKHQ FRPSRQHQWV RI WKH 3LWPDQ $5( DUH H[n SDQGHG RXW ZLOO LQYROYH WKH VDPH W\SH RI LQWHJUDO DV JLYHQ LQ /HPPD WKHUHE\ OHDGLQJ WR VLPSOLILHG HYDOXDWLRQV $Q ([DPSOH 7KHRUHP FDQ EH XVHG WR HYDOXDWH D 3LWPDQf $5( IRU VRPH SDUWLFXODU GLVWULEXWLRQV ZKHQ WKH XQNQRZQ SDUDPHWHU LV PLVVSHFLILHG $Q\ PHQWLRQ RI $5( LQ WKLV GLVVHUWDWLRQ LPSOLFLWO\ UHIHUV WR 3LWPDQ DV\PSWRWLF UHODWLYH HIILFLHQF\ 7KH $5( H[SUHVVLRQ LQ WKH WKHRUHP FDQ DOVR EH HPSOR\HG WR FRPSDUH WKH PL[HG PRGHO VFRUHV WHVW ZLWK WKH OLQHDU UDQN WHVW GHULYHG XQGHU WKH XVXDO ORFDWLRQVKLIW PRGHO 6FRUH IXQFWLRQV VXFK DV WKRVH IRU WKH :LOFR[RQ DQG ORJUDQN WDNH WKH SODFH RI SFK^Xff 7KH PL[HGPRGHO VFRUHV DUH VXEVWLWXWHG LQWR I!W^Xf $Q LOOXVWUDWLRQ XVLQJ WKH QRUPDO GLVWULEXWLRQ IRU )[ f§ $f LV QRZ SUHVHQWHG 5HFDOO WKDW -RKQVRQ HW DO f FKRVH WKH QRUPDO GLVWULEXWLRQ WR GHULYH D PL[HG PRGHO VFRUH IXQFWLRQ )LUVW ZH QRWH WKDW EHFDXVH !Xf GRHV QRW KDYH D FORVHGIRUP WKH H[SHFWHG VFRUH FRUUHVSRQGLQJ WR ;M PXVW EH QXPHULFDOO\ HYDOXDWHG $ JHQHUDO H[SUHVVLRQ IRU WKH H[SHFWHG VFRUH LV 1O F f§7MI!^XLfXLfn ; 8Lf^1 GXL  f§f9 f§f .1RZ UHIHU WR 7KHRUHP 6LQFH DOO FRPSRQHQWV RI WKH ILUVW GHULYDWLYH I!?Xf $H$) f3f I)+ Xff H[FHHG FRQGLWLRQ Lf KROGV $OVR FRQGLWLRQ LLf KROGV IRU DQ\ $ VLQFH E\

PAGE 42

7DEOH 3LWPDQ $5( IRU PLVVSHFLILHG $ PL[HG QRUPDO GLVWULEXWLRQ $ $FL VWUDLJKWIRUZDUG LQWHJUDWLRQ L I!XfGX H$r f§ R 7KLV SURYLGHV WKH DV\PSWRWLF SURSHUWLHV RI Y ZKHQ WKH XQGHUO\LQJ VXUYLYDO GLVWULEXn WLRQ LV PL[HG QRUPDO )RU VWXG\LQJ PLVVSHFLILFDWLRQ RI $ 7DEOH LV DQ H[WHQVLRQ RI 7DEOH LQ -RKQn VRQ HW DO f $JDLQ E\ VWUDLJKWIRUZDUG LQWHJUDWLRQ WKH DOJHEUDLF IRUP RI WKH $5( IRU PLVVSHFLILHG $ LV HII$FIF $If He$"F f$$FKff H$" f§ 1RZ ZH WXUQ WR PRGHO PLVVSHFLILFDWLRQ 7DEOH LV DQ H[WHQVLRQ RI 7DEOH LQ -RKQVRQ HW DO f ,Q FRPSDULVRQ WR WKH QRUPDO VFRUHV WHVWV RI )LVKHU t
PAGE 43

7DEOH 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG QRUPDO GLVWULEXWLRQ $ IRU PL[HGPRGHO VFRUH f DQG YDQ GHU :DHUGHQ f 7DEOH LQGLFDWHV WKDW WKH PL[HGPRGHO VFRUHV KDYH D GLVWLQFW DGYDQWDJH IRU $ 7KLV ZDV SRLQWHG RXW LQ 7DEOH RI -RKQVRQ HW DO f 7KH 6&( GDWD H[DPSOH LQ -RKQVRQ HW DO f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f $GGLWLRQDOO\ WKH LQYDULDQFH WR

PAGE 44

PRQRWRQH WUDQVIRUPDWLRQV LV D ZRUWKZKLOH IHDWXUH 7KH SURSHUW\ RI ORFDOO\ PRVW SRZHUIXO UDQN WHVWV LV DSSHDOLQJ DV ZHOO VLQFH LW LV XVXDOO\ WKH FDVH WKDW VXFK UDQN WHVWV GR ZHOO IRU QRQORFDO DOWHUQDWLYHV ([WHQVLRQV RI WKHVH SURFHGXUHV FRQVWLWXWH WKH WKUXVW RI WKH UHPDLQGHU RI WKLV PDQXVFULSW 2QH WRSLF LV WKH XVH RI RWKHU GLVn WULEXWLRQDO IRUPV IRU )[ $f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

PAGE 45

&+$37(5 0(7+2'6 )25 &(1625(' '$7$ ,QWURGXFWLRQ ,QYHVWLJDWLRQ RI WKH SURSHUWLHV DVVRFLDWHG ZLWK D OLQHDU UDQN WHVW VWDWLVWLF IRU FHQVRUHG GDWD UHTXLUHV D GLIIHUHQW DSSURDFK WKDQ WKDW IRU WKH FDVH ZKHUH QR FHQVRULQJ RFFXUV $ XVHIXO WHFKQLTXH LQ VLPLODU DQG FRPPRQ LQIHUHQFH VLWXDWLRQV LV WR FDVW WKH WHVW VWDWLVWLF DV D VWRFKDVWLF LQWHJUDO 7KLV HQDEOHV WKH XVH RI WKH WKHRU\ RI FRXQWLQJ SURFHVVHV DQG PDUWLQJDOHV WR GHULYH DV\PSWRWLF SURSHUWLHV $DOHQ f DQG *LOO f ZHUH UHVSRQVLEOH IRU PXFK RI WKH IRXQGDWLRQDO ZRUN RI WKLV DSSURDFK 7KHLU ILQGLQJV KDYH EHHQ DSSOLHG QXPHURXV WLPHV E\ UHVHDUFKHUV LQ WKH DUHD RI FHQVRUHG GDWD OLQHDU UDQN VWDWLVWLFV ,Q 6HFWLRQ 7ZR RI WKLV FKDSWHU D UDQNEDVHG OLNHOLKRRG LV GHULYHG IRU FHQVRUHG GDWD XQGHU WKH PL[WXUH PRGHO f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

PAGE 46

Y WKDW PD\ EH XVHIXO LQ SUDFWLFDO DSSOLFDWLRQV 3URSHUWLHV RI Y XQGHU DOWHUQDWLYH K\SRWKHVHV DUH SUHVHQWHG LQ 6HFWLRQ 6L[ 7KH /LQHDU 5DQN 7HVW 6WDWLVWLF Y 5DQN /LNHOLKRRG IRU WKH 'DWD .DOEIOHLVFK DQG 3UHQWLFH f GHILQHG D FHQVRUHG GDWD UDQN VWDWLVWLF DV WKH VHW RI DOO UDQN YHFWRUV RI XQFHQVRUHG VXUYLYDO WLPHV WKDW FDQ JLYH ULVH WR WKH REVHUYHG UDQNV RI WKH GDWD 7KH SUREDELOLW\ RI WKH REVHUYHG FHQVRUHG GDWD UDQN VWDWLVWLF 3Uf FDQ EH FDOFXODWHG E\ VXPPLQJ XS WKH SUREDELOLWLHV RI DOO SRVVLEOH XQGHUO\LQJ UDQN YHFWRUV JLYHQ WKH FHQVRULQJ SDWWHUQ RI WKH GDWD $OO SRVVLEOH UDQNLQJV RI WKH VDPSOH WKDW PLJKW EH REVHUYHG LI ZH FRXOG PHDVXUH WKH DFWXDO VXUYLYDO WLPHV IRU HDFK VXEMHFW DUH DGGHG WRJHWKHU WR JHW 3Uf 7KH .DOEIOHLVFK DQG 3UHQWLFH f IRUPXODWLRQ GRHV QRW WDNH LQWR DFFRXQW WKH RUGHU RI WKH FHQVRUHG REVHUYDWLRQV LQVLGH DQ LQWHUYDO GHILQHG E\ WZR DGMDFHQW RUGHUHG XQFHQVRUHG YDOXHV 6DFULILFH RI WKLV RUGHULQJ LQIRUPDWLRQ VKRXOG EH QHJOLJLEOH LQ WKH UHODWLYH SUHVHQFH RI D GHFHQW QXPEHU RI XQFHQVRUHG REVHUYDWLRQV 3UHQWLFH f 5HFDOO WKH PL[WXUH PRGHO DW f DV *[ 7 $f *[f WW)[ $f f§ Uf7[f ZLWK $ DQG U ( >@ $ UHSUHVHQWDWLRQ RI 3Uf IRU GDWD VDPSOHG XQGHU PRGHO f DQG WKH UDQGRP FHQVRUVKLS VWUXFWXUH LV

PAGE 47

3Uf f f f Q 0Rfnr1 :r $f }frf f@: rfrfn[rf rB [ >)[Of f@PrB$L>[)[Wf $f [f)[Lf f@0L G[A\ f %HFDXVH WKH FHQVRULQJ GLVWULEXWLRQV DUH DVVXPHG WR QRW GHSHQG RQ [ DQG $ WKH FHQVRULQJ GLVWULEXWLRQV DUH QRW LQFOXGHG LQ WKH OLNHOLKRRG H[SUHVVLRQ DW f 7KLV fUDQN OLNHOLKRRGf DOORZV JHQHUDWLRQ RI VFRUHV LQ OLQHDU UDQN VWDWLVWLFV IRU YDULRXV FKRLFHV RI )[ $f $ $ PHFKDQLVP IRU GHULYLQJ OLQHDU UDQN WHVWV IURP 3Uf SDUDOOHOV WKH WHFKQLTXH IRU FRQVWUXFWLQJ ORFDOO\ PRVW SRZHUIXO UDQN WHVWV ZLWK XQFHQVRUHG GDWD IRU WKH XVXDO W\SHV RI DOWHUQDWLYHVf§ORFDWLRQ VFDOH DQG UHJUHVVLRQ HJ +£MHN DQG 6LG£N f $ *HQHUDO )RUP 7KHUH DUH WKUHH FRQGLWLRQV RI +£MHN DQG 6LG£N S f WKDW DUH VXIILFLHQW IRU GHULYLQJ ORFDOO\ PRVW SRZHUIXO UDQN WHVWV $ YHUVLRQ RI WKHVH FRQGLWLRQV DSSURSULDWH IRU WKH SXUSRVHV RI WKLV GLVVHUWDWLRQ LV Lf )RU VRPH H WKH VXUYLYDO IXQFWLRQ *[ W$f DQG WKH GHQVLW\ J[ [ $f DUH FRQWLQXRXV LQ [ [ f > H@ IRU HYHU\ [ LLf 7KH OLPLWV G*[ [ $f B *[ [ $f f§ *[ $f B *[ [ $f f§ )[f ; r nf‘2 ; Wr 7 DQG

PAGE 48

GJ[ 7 $f_ B J^[ WW $f J[ $f B J[ W $f I[f GO7 Y R "Uf§2 U LU! 7 H[LVW IRU HYHU\ [ LLLf RR GJ[ 7 $f 7 G[ RR IRU HYHU\ $ DQG 22 G*[ U $f 7 rf )[f G[ RR IRU HYHU\ $ :H QRZ LQWURGXFH WKH JHQHUDO IRUP RI X LQ WKH IROORZLQJ WKHRUHP 7+(25(0 &RQVLGHU WKH WZRVDPSOH GDWD VLWXDWLRQ JLYHQ E\ f *[f *[ 7 $f U)[ $f f§ Wf)[f 6XSSRVH WKH VXSSRUW RI )[f LV FRQWDLQHG ZLWKLQ WKDW RI )[ $f DQG WKHUH H[LVWV D SRVLWLYH FRQVWDQW % RR VXFK WKDW f f§RR Y n 7KHQ D UDQN WHVW IRU WHVWLQJ + 7 YV +D LW LQ WKH PRGHO f FDQ EH EDVHG RQ WKH VWDWLVWLF N 9 ^]nf&W 0&!f W O f

PAGE 49

ZKHUH L ‘ffmm L Q L LWLL f 8O f§XN L DQG F WZQmLmcUA` 8M8r Lf§ f ZLWK DQG ` )+OXff rXf ))fOXf$f B ` ))+ Qf $f A)+OXff Xf 3URRI )ROORZLQJ -RKQVRQ HW DO S f D SURRI RI 7KHRUHP FDQ EH JLYHQ E\ YHULI\LQJ WKH WKUHH FRQGLWLRQV RQ SDJH RI WKLV PDQXVFULSW )RU VRPH H Lf WKH VXUYLYDO IXQFWLRQ *[ WW $f f§ Qf)[f WW)[ $f DQG WKH GHQVLW\ J[ WW $f f§ WWf[f U[ $f ZLOO EH FRQWLQXRXV LQ WW U ( > H@ IRU HYHU\ [ 7KH RQHVLGHG QDWXUH RI WKH LQWHUYDO > H@ GRHV QRW DIIHFW WKH YDOLGLW\ RI +£MHN DQG 6LGDNfV FRQGLWLRQV DFFRUGLQJ WR WKH DUJXPHQW RI -RKQVRQ HW DO f 1H[W LLf WKH OLPLWV *[ 7 $f f§ *[ $f *[f )[f OLP OLP UUf§2 U LUf§} 7 M f§ 7f)[f U)[ $f f§ )[f 7f§ U )[ $f f§ )[f DQG OLP 7f§r J^[ WW $f J[ $f OLP J^[f I[f 7 MWf§! 7

PAGE 50

OLP A a $f a LUA2 7 I[$fI[f H[LVW IRU HYHU\ [ DQG LLLf RR _*[ 7 $f f§ *[ $f_ *[ $f _I r $f I ]f_ J[ $f G[ f§ 22 -Qr$fZB ")[f f§ 22 RR )[f )[ $f aA7 )[ $f )[f I[fG[ RR Of ):,f f§ 22 I[fG[ G[ % RR ZKHQ WKH VXSSRVLWLRQ DW f KROGV DQG RR ?J^[ 7 $f f§ J[ $f_G[ f§ 22 RR ,r $f [f_G[ f§22 RR I RR _[$f_G[ _[f_ G[ f§22 f§RR RR 7R GHULYH WKH OLQHDU UDQN WHVW VWDWLVWLF EDVHG RQ f UHIHU WR 3UHQWLFH f DV D EDVLV IRU WKH IROORZLQJ UHSUHVHQWDWLRQV &RQGLWLRQV LfLLLf EHLQJ VDWLVILHG HQVXUHV WKDW GLIIHUHQWLDWLRQ DQG LQWHJUDWLRQ LQWHUFKDQJH LV SHUPLVVLEOH 7KH UDQN SUREDELOLW\ f FDQ EH H[SUHVVHG DV 3Uf M Q 3L rf rfrfrIFf

PAGE 51

ZKHUH 3[ UHSUHVHQWV WKH FRQWULEXWLRQ WR WKH OLNHOLKRRG RI IDLOXUH WLPH DQG WKH FHQVRUHG REVHUYDWLRQV efL ;fP FRQWDLQHG LQ WKH LQWHUYDO >[Wf;ff 3L rc!fff0>7]cf $f [fL [ >)[Lf fSf>[)[R $f rf)r f@n G[Yf 7KHQ G ORJ 3Uf GU G3Uf GU I 30 3Uf >ef‘‘ Q S G[Lf M  M 30 30 >‘‘‘> Wn 30 >‘ W!3 Q SL G[Lf M L L Q SL G[Lf M L L f (YDOXDWLRQ RI WKH ULJKWKDQG VLGH RI f DW WKH QXOO YDOXH U SURYLGHV WKH IRUP RI WKH OLQHDU UDQN VWDWLVWLF JLYHQ E\ f 7R LOOXVWUDWH WKLV ILUVW QRWH WKDW 3Uf f f ‘ Q I[Lff)[LffPn G[LK Q ;f;rf } ZKLFK FDQ EH GLUHFWO\ LQWHJUDWHG 3UHQWLFH f WR DUULYH DW WKH UHVXOW 3Uf N Q U L O f 1H[W REVHUYH WKDW N G (OAJS ;6 GQ 7f§ RfOR6rmff Pm 0Lf?RJ)[^Lff

PAGE 52

rf ORJ>U[Wf $f rUf[Lff@ 0 ORJ>[)[Wf $f [f)[Wff@` \  [Of $f [Wff  Uf N[f $f Uf[f@ )[ $f )[Wff ? n >U)[Lf $f Uf)[Wff@ e ? 0 7 7 N [Of $f [Wff W KI )[Wf $f )[fff L L ( R ‘$f r‘ff Qrmf 0 AA $f f 3XWWLQJ ff WRJHWKHU DQG WKHQ XVLQJ WKH VXEVWLWXWLRQ 8M f§ )[Mff \LHOGV WKH OLQHDU UDQN WHVW VWDWLVWLF JLYHQ E\ f ZLWK VFRUHV f DQG f ’ 7KH VFRUH IXQFWLRQV f ZHUH UHSRUWHG LQ -RKQVRQ HW DO f IRU WKH VLWXDn WLRQ RI XQFHQVRUHG GDWD DQG ORFDWLRQVKLIW IRUP IRU )[ $f &RQRYHU DQG 6DOVEXUJ f GHULYHG VSHFLILF VFRUHV FRUUHVSRQGLQJ WR D /HKPDQQDOWHUQDWLYH FKRLFH RI )[ $f 7KH QH[W FRUROODU\ VXPPDUL]HV WKH QRWLRQ WKDW WKH UHVXOWLQJ OLQHDU UDQN VWDWLVWLFV SURYLGH ORFDOO\ PRVW SRZHUIXO UDQN WHVWV LQ WKH XQFHQVRUHG GDWD FDVH &252//$5< 8QGHU WKH FRQGLWLRQV RI 7KHRUHP VXSSRVH WKDW WKHUH DUH QR FHQVRUHG REVHUYDWLRQV 7KH ORFDOO\ PRVW SRZHUIXO UDQN WHVW /0357f LV JLYHQ E\ WKH IRUP f ZLWK WKH VFRUHV f 3URRI 6HW 0L LQ f 7KLV JLYHV f WKH /0357 DV GLVFXVVHG LQ 6HFWLRQ ’ 7KH IROORZLQJ OHPPD FRQWDLQV D VXIILFLHQW FRQGLWLRQ IRU f LQ 7KHRUHP ZKHQ )[ $f )[ f§ $f

PAGE 53

/(00$ /HW % EH D SRVLWLYH FRQVWDQW VXFK WKDW % RR DQG OHW EH GHILQHG DV LQ f RU f ,I )[ $f )[ f§ $f WKHQ I!XfGX f§ U)O f§ Xf f§ $f I)anOXff GX % LPSOLHV WKDW 22 )[ $f )[f I^[fG[ % 3URRI 0DNH WKH VXEVWLWXWLRQ X f§ )[f DQG LQWHJUDWHE\SDUWV WR VKRZ RR Y n > ORJO Xf))aO f§ Xf f§ $f@A ORJ Xf I)nOXf$f GX f 1RZ WKH ILUVW WHUP RQ WKH ULJKWKDQG VLGH RI f FRQWDLQV WKH IRUP RR f ZKHQ HYDOXDWHG DW X DQG WKXV UHTXLUHV VRPH H[WUD KDQGOLQJ WR VKRZ WKDW LWV YDOXH LV ]HUR /HW GHQRWH WKH LQGLFDWRU IXQFWLRQ ZKLFK WDNHV RQ WKH YDOXH ZKHQ WKH HYHQW $ RFFXUV DQG RWKHUZLVH /HW ; EH WKH UDQGRP YDULDEOH ZLWK WKH VXUYLYDO IXQFWLRQ ) 7KH VXEVWLWXWLRQ [ ) ; f§ Xf OHDGV WR OLP >f§ ORJO f§ Xf)) r f§ Xf f§ $f_ OLP f§ ORJ)[ff)[ f§ $f .P OrJ)[ffeM>[![B$@ ?LP6>?RJ);fffO>[![$@ IRU f§ ORJ)f LV PRQRWRQH LQFUHDVLQJf -MPA+RJ&):f@

PAGE 54

ILPe>ORJ);ff@->MU[B$@ E\ WKH 0RQRWRQH &RQYHUJHQFH 7KHRUHP DQG WKH IDFW WKDW L  > ORJ);ff@ ORJO XfGX R 7KH VHFRQG WHUP RQ WKH ULJKWKDQG VLGH RI f LV DOVR ILQLWH VLQFH ORJ Xf I)O OXf$f mff GX M >LRJL Xf@GXM M\ f %f RR UI)anOXf$\ Omff GX E\ WKH &DXFK\6FKZDU] LQHTXDOLW\ DQG E\ WKH VXIILFLHQW FRQGLWLRQ RI WKH OHPPD ’ 7KH FRQGLWLRQ LQ /HPPD LV FORVHO\ UHODWHG WR ODUJHVDPSOH SURSHUWLHV IRU WKH OLQHDU UDQN VWDWLVWLF Y $V FDQ EH VHHQ IURP 7KHRUHP LW LV WKH SULPDU\ FRPSRQHQW RI DQ H[SUHVVLRQ IRU WKH DV\PSWRWLF YDULDQFH RI Y ZLWK XQFHQVRUHG GDWD ZKLFK LV UHTXLUHG WR EH ILQLWH $OWHUQDWH 6XPPDWLRQ )RUP IRU Y ,W KDV EHHQ FRPPRQ DQG FRQYHQLHQW LQ WKH OLWHUDWXUH WR GLVSOD\ OLQHDU UDQN VWDWLVn WLFV IRU WHVWLQJ HTXDOLW\ RI VXUYLYDO GLVWULEXWLRQV LQ WKH IRUP RI D VXP RI ZHLJKWHG GLIIHUHQFHV EHWZHHQ WKH QXPEHU RI REVHUYHG GHDWKV DQG WKH QXPEHU RI FRQGLWLRQDOO\ fH[SHFWHGf GHDWKV &RQGLWLRQLQJ LV GRQH RQ WKH SULRU IDLOXUH DQG FHQVRULQJ KLVWRU\ REVHUYHG 7DURQH DQG :DUH f DQG 3UHQWLFH DQG 0DUHN f IRUPDOO\ GLVFXVV

PAGE 55

WKLV IRUP IRU VRPH RI WKH PRUH ZHOONQRZQ WHVW VWDWLVWLFV $XWKRUV VXFK DV +DUULQJn WRQ DQG )OHPLQJ f FRQVLGHU ZKROH FODVVHV RI VWDWLVWLFV WKDW DUH GLVWLQJXLVKHG E\ WKH FKRLFH RI WKH ZHLJKWV RQ WKH GLIIHUHQFHV 5HFDOO WKH GHILQLWLRQ 5L RI WKH VL]H RI WKH ULVN VHW LQ 6HFWLRQ /HW 5X EH WKH QXPEHU RI WUHDWHG VXEMHFWV LQ WKH ULVN VHW DW IDLOXUH WLPH =f DQG 5R EH WKH FRUUHVSRQGLQJ QXPEHU LQ WKH FRQWURO JURXS 1RWH WKDW 5D 5X 5 7KH SUHVHQW JRDO LV WR UHSUHVHQW L! GHILQHG LQ fff LQ WKH IROORZLQJ IRUP ( Zn ]f a f ZKHUH :L F & f LV WKH ZHLJKW IXQFWLRQ DVVRFLDWHG ZLWK WKH IDLOXUH WLPH DQf $ VXIILFLHQW FRQGLWLRQ IRU L WR KDYH WKH IRUP DW f DQG f LV WKDW WKH VFRUHV F DQG & VDWLVI\ 5L&LL F ^5L f& r OIF f ZKHUH &R 7KH FRQGLWLRQ DW f ZDV ILUVW GHULYHG E\ 3UHQWLFH DQG 0DUHN f ZKR XVHG LW WR UHSUHVHQW WKH ORJUDQN 0DQWHO &R[ f *HKDQ f DQG 3HWR t 3HWR f VWDWLVWLFV LQ WKH IRUP f 6LQFH Y FDQ EH UHZULWWHQ 3UHQWLFH DQG 0DUHN f DV WKH VXP RI WKH IRUP f DQG D TXDQWLW\ } ( }f 8f WWf ( &L IW& &Lff f ; 8n n ZKHUH WKH VHFRQG WHUP RQ WKH ULJKWKDQG VLGH RI f HTXDOV ]HUR ZKHQ f

PAGE 56

KROGV ZH FRQFHQWUDWH RQ VKRZLQJ WKDW WKH UHODWLRQ f LQGHHG KROGV IRU WKH PL[HGPRGHO VFRUHV F DQG &W ,Q IXOO QRWDWLRQ f LV H[SUHVVHG DV U:nR f 3rL fLS Gff ‘ 8O8r [ Y )) mff 8Lf§Xr n ? 9 9 m N [ Q a XMfPM M L ([SDQGLQJ WKH DERYH IXOO YHUVLRQ RI f \LHOGV LM Q 5c ))LOXcff W[LXIF n 9 Y N [ Q M L &DQFHOOLQJ FRPPRQ WHUPV RQ ERWK VLGHV DQG VLPSOLI\LQJ JLYHV IRU f ‘ Lf$ff Q 5L 8 f ))LO WLLff )8OQf$f?A IBLLf§mfff MQA 8Lf f ) f ))B LWf $fn [ ))Xff mLfffmr n ? ? WQ N [QAG XMfPM GXM f

PAGE 57

$VVXPH WKDW ) :H DGDSW D WHFKQLTXH HPSOR\HG E\ 0HKURWUD 0LFKDOHN DQG 0LKDONR f 6WDUWLQJ ZLWK WKH VHFRQG WHUP RQ WKH ULJKWKDQG VLGH RI f ILUVW LQWHJUDWH RXW XL 8N WR JHW LQ ,, I OXf$f / -R ))nOX2f cf W [ --^)MO f§ 8MfPM GXM`GXL M L I"Lf fQAWLA£` -8_ -2 U )) XLf $f ) XM.nGYL f Xf 1H[W DSSO\ WKH LQWHJUDWLRQE\SDUWV WHFKQLTXH WR WKH LQWHJUDO RYHU X /HW 8 )) 8Lf $f DQG G9 )O 8Lf5nGXL %\ WKH VHTXHQFH RI UHODWLRQV 9 ) O Pf )^\f 8L I\fG\ GXL G\ B GXL I^\ff LW IROORZV WKDW G8B GXW aI) a 8Lf $f G)aO XMf GXL I)OO8Lf$f/ )O 8Mf $f )+O2f

PAGE 58

DQG 9 5 5L X$5fa9 mf 8VH RI WKHVH UHODWLRQV LQ WKH ODVW LQWHJUDO RI f JLYHV >r ))? 8Lf $f5L^O 8Lf5nGXL f U[UnDmff$0>SAU2mcf LOW ‘))?O8Lf L"  AGm‘f $f -M BXf+U mL An f‘f $f! ZKf/ 5L U WX Pf§ L AOX2U$f )rOXff / m XLf $fO 5L L I^)? m‘f $f f§ I 5L f§ LXBL I)nO8Lff f§ Xfn nGX 7KHQ ZLWK WKH DGGLWLRQDO UHODWLRQ LPSOLHG E\ WKH GHILQLWLRQ RI 5M 77OM f§ 5M 5Mf§L f§ VXEVWLWXWHG LQWR f ZH JHW L"LfD Lf rff I fff fQ ^5LXMfPfGXM` -X -2 fB [A7Lf)n,fLf$ff8Lf -8Lf§ fn2 MBL + GmL f 6HFWLRQ

PAGE 59

5L L I)?O8Lf$f m‘ff [f§> ; 5Wa X A XB R ))B XBLf $f )LO XBLf+L nGXLL UO }O I f f n Q ^50XL7fGX` MXBL -R mf $f )+OXff &BL f f§ F f )O Wfrrr ZKLFK LV MXVW D UHH[SUHVVLRQ RI f RU f VLQFH F DQG & DUH RI WKH VDPH IRUP DIWHU LQWHJUDWLRQ RYHU XL X 1RZ LI 5 ZH KDYH N L DQG PMW +HUH WKH FRQGLWLRQ f UHGXFHV WR &N &N f 7KH UHODWLRQ f FDQ EH YHULILHG DV IROORZV &N I ?I)?O8Nf$f n )+OXff ; fff B -XN rn M O I Ur?))OOXNLf$f -8LT f§ rO OLIFOf IF [A'OXAfAn ,,: L L I URUA)+O8IF4L$f -O > O8$f IF [)rLO OLMIHLfA --^L M L f§ &IFL

PAGE 60

6WRFKDVWLF ,QWHJUDO )RUP IRU Y 7KH VWDWLVWLF DW f FDQ EH UHDGLO\ WUDQVODWHG LQWR WKH IRUP RI D VWRFKDVWLF LQWHJUDO 5HFDOO WKDW WKH FRQWURO JURXS VDPSOH LV ODEHOOHG VDPSOH WKH WUHDWPHQW JURXS VDPSOH LV ODEHOOHG VDPSOH 5HFDOO WKH QRWDWLRQ GHILQHG LQ 6HFWLRQ DQG UHFDOO WKH GHILQLWLRQ RI LQGLFDWRU IXQFWLRQ ;rf RU DFFRUGLQJ WR ZKHWKHU WKH HYHQW $ RFFXUV RU GRHV QRW RFFXU )RU WKH JURXSV U ZLWK VXUYLYDO WLPH UDQGRP YDULDEOHV ;UM M f§ 1U DQG FHQVRULQJ LQGLFDWRUV DV GHILQHG LQ 6HFWLRQ f 6UM M 1U OHW .[f [6L f 1RWH $IU[f LV WKH QXPEHU RI IDLOXUHV IRU JURXS U WKDW RFFXU QR ODWHU WKDQ WLPH [ $OVR OHW
PAGE 61

DQG G$U[f $IU^[f f§ 1U[f§f 7KH DVVXPSWLRQV RI FRQWLQXRXV VXUYLYDO GLVWULEXWLRQV LPSOLHV WKDW WKH SUREDELOLW\ RI WLHV DPRQJ WKH [Sf LV ]HUR 7KXV ZLWK SUREDELOLW\ G$IL[f ]LE LI[ rR RWKHUZLVH DQG G$R[f mff LI ; ;fRWKHUZLVH 6R D VWRFKDVWLF LQWHJUDO H[SUHVVLRQ IRU Y FDQ EH ZULWWHQ DV Y A 5X 5R 5X /ZR mU 5L 5 B ]]L? a 5Lf IfrZ;!IfLrRf URR Z[f -f§RR URR 8O[f f§ 22 b[f U[fM A[A[f G$? [f > Z[f G$LR[f MR >< [M ? GM?IL[f G$fR[f_ )Df U[f<[f )[f f ZKHUH Z[f & f§ &L ;f [ [W &RQGLWLRQV IRU $V\PSWRWLF 3URSHUWLHV 8QGHU +S 7KH IRUPXODWLRQ RI Y DV D VWRFKDVWLF LQWHJUDO DOORZV XV WR DSSO\ WKH PDUWLQJDOH WKHRU\ RI *LOO f ZLWK VXLWDEOH DGDSWDWLRQV +LV ZRUN LQFOXGHV WKH VWDWHPHQW RI FHUWDLQ FRQGLWLRQV WKDW DUH VXIILFLHQW WR GHULYH DQ DV\PSWRWLF GLVWULEXWLRQ IRU D

PAGE 62

SURSHUO\ VWDQGDUGL]HG YHUVLRQ RI X 5HFDOO WKH GHILQLWLRQV RI I!Xf DQG Xf DW f DQG f UHVSHFWLYHO\ 7KH QRWDWLRQ RI I!Xf DQG I!Xf DV VFRUH IXQFWLRQV WKDW FRUn UHVSRQG WR XQFHQVRUHG DQG FHQVRUHG REVHUYDWLRQV UHVSHFWLYHO\ ZDV LQWURGXFHG E\ 3UHQWLFH f LQ WKH IUDPHZRUN RI UHJUHVVLRQ PRGHOV 6XEVHTXHQWO\ WKH QRWDWLRQ KDV EHHQ XVHG LQ WKH DUHD RI FHQVRUHG GDWD OLQHDU UDQN VWDWLVWLFV +DUULQJWRQ DQG )OHPLQJ &X]LFN f 7KXV ZH DGRSW WKH QRWDWLRQ IRU WKH UHPDLQGHU RI WKLV GLVVHUWDWLRQ ,Q WKLV VHFWLRQ ZH OHDG XS WR VXIILFLHQW FRQGLWLRQV WKDW SHUPLW LQYHVWLJDWLRQ RI WKH DV\PSWRWLF SURSHUWLHV RI WKH FHQVRUHG GDWD WHVW EDVHG RQ Y ,Q WKH SURFHVV ZH ZLOO VKRZ WKDW IRU ODUJH VDPSOHV WKH H[SHFWHG VFRUHV F DQG & LQ Y FDQ EH UHVSHFWLYHO\ UHSODFHG ZLWK DSSUR[LPDWH VFRUHV WKDW DUH HDV\ WR FRPSXWH $SSUR[LPDWH 6FRUHV 7KH FRPSXWDWLRQDO FRPSOH[LWLHV DVVRFLDWHG ZLWK OLQHDU UDQN SURFHGXUHV WKDW XVH H[SHFWHG YDOXH VFRUHV F[ e>!Xf@ KDV ORQJ EHHQ UHFRJQL]HG LQ WKH OLWHUDWXUH )RU XQFHQVRUHG GDWD OLQHDU UDQN SURFHGXUHV GHVLJQDWHG WR GHWHFW D VKLIW LQ D GLVn WULEXWLRQ IRU H[DPSOH WKH QRUPDO YDQ GHU :DHUGHQ f DSSUR[LPDWH VFRUHV F )O f§ Af ZKHUH f§ ) LV WKH FXPXODWLYH GLVWULEXWLRQ IXQFWLRQ RI WKH VWDQGDUG QRUPDO GLVWULEXWLRQ DUH PXFK HDVLHU WR HYDOXDWH WKDQ WKH H[SHFWHG VFRUHV ,Q IDFW WKH QRUPDO H[SHFWHG VFRUHV DUH WKH e=ffI OL9 ZKHUH =[f LV WKH ]WK RUGHU VWDWLVWLF LQ D UDQGRP VDPSOH RI VL]H 1 IURP WKH VWDQGDUG QRUPDO GLVWULn EXWLRQ 7KHVH VFRUHV LQYROYH LQWHJUDOV WKDW GR QRW KDYH FORVHGIRUP H[SUHVVLRQV 0RUH VR LQ WKH FHQVRUHG GDWD FDVH WKH H[SHFWHG VFRUHV LQYROYH LQWHJUDOV WKDW GR

PAGE 63

QRW KDYH VWUHDPOLQHG FORVHG IRUPV DQG UHTXLUH QXPHULFDO LQWHJUDWLRQ PHWKRGV WR EH HYDOXDWHG 3UHQWLFH f FRQMHFWXUHG WKDW WKH H[SHFWHG VFRUHV F DQG IURP WKH UDQN OLNHOLKRRG KH GHULYHG FRXOG EH DSSUR[LPDWHG E\ WKH UHVSHFWLYH VFRUHV I! f§ )[Tff DQG f§ )[fff $ VXEVHTXHQW DUWLFOH E\ &X]LFN f FRQILUPV WKH WUXWK RI WKH FRQMHFWXUH ZLWK WKH UHTXLUHPHQW WKDW VRPH IDLUO\ PLOG FRQGLWLRQV RQ WKH XQFHQVRUHG VFRUH IXQFWLRQ !Xf EH VDWLVILHG 7KH UHVXOWLQJ DV\PSWRWLF HTXLYDOHQFH RI WKH OLQHDU UDQN WHVWV EDVHG RQ WKH WZR W\SHV RI VFRUHV LV RQH LQ WKH VHQVH WKDW WKH GLVWDQFH EHWZHHQ WKH WZR WHVW VWDWLVWLFV FRQYHUJHV WR ]HUR LQ DEVROXWH PHDQ DV 1 f§ RR %HIRUH VWDWLQJ &X]LFNfV f PDLQ UHVXOW ZH VWDWH WZR OHPPDV /(00$ 7KH IROORZLQJ UHODWLRQVKLS KROGV IRUL Xf f§ I SYfGY n/O X 3URRI 8WLOL]H WKH WUDQVIRUPDWLRQ Y f§ )Xf WR JHW I!YfGY -X L ^ InOYff OfG ^))nOW2W$ffnf§Xf )^)?f $f )L)nL f§ Xf $f f§ f§ Xf ))fOXf $f f§ Xf VR WKDW GLYLGLQJ ERWK VLGHV E\ f§ X DQG VXEVWLWXWLQJ ZLWK WKH UHODWLRQ ))aO f§ Xff f§ X FRPSOHWHV WKH SURRI ’

PAGE 64

/HPPD SURYLGHV D ZHOOGHILQHG IXQFWLRQDO UHODWLRQVKLS EHWZHHQ XQFHQVRUHG DQG FHQVRUHG VFRUH IXQFWLRQV 0DWKHPDWLFDO FRQGLWLRQV RQ VXFK DV FRQWLQXLW\ ZLOO LPSO\ VLPLODU RQHV IRU !Xf &RQVLGHU WKH IROORZLQJ WKUHH VDPSOH TXDQWLWLHV WR HVWLPDWH WKH VXUYLYDO IXQFWLRQ QRn )NP[f Q A rm!r f )3[f 77 5M f )D[f H[S f ZKHUH 5M LV WKH VL]H RI WKH ULVN VHW DW WLPH ;Mf 7KH HVWLPDWRU ).0 LV WKH VRFDOOHG SURGXFWOLPLW HVWLPDWRU .DSODQ DQG 0HLHU f 7KH HVWLPDWRU )S LV GLVFXVVHG LQ 3UHQWLFH f DQG )$ ZDV SURSRVHG E\ $OWVKXOHU f )RU JHQHUDWLQJ FHQVRUHG GDWD OLQHDU UDQN WHVW VWDWLVWLFV LQ WKH FDVH RI ORFDWLRQ DOWHUQDWLYHV D MXGLFLRXV FKRLFH IURP WKHVH WKUHH HVWLPDWRUV KDV OHG WR QLFH FORVHGIRUP H[SUHVVLRQV IRU H[SHFWHG DQG DSSUR[LPDWH VFRUHV 3UHQWLFH +DUULQJWRQ DQG )OHPLQJ f ,Q QXPHULFDO FRPSXWDWLRQV IRU ODUJHVDPSOHV DQ\ RQH RI WKH WKUHH HVWLPDWRUV LV UHDVRQDEOH 7KH DFWXDO UHODWLRQVKLS &X]LFN f DPRQJ WKH WKUHH LV ).0^[f )D^[f )S[f IRU DOO [ 8QOHVV VSHFLILHG RWKHUZLVH ) ZLOO EH WKH JHQHUDO UHSUHVHQWDWLRQ IRU WKH WKUHH HVWLPDWRUV 2QH GDQJHU LQ WKH XVH RI f LV ZKHQ LW WDNHV RQ WKH YDOXH DQG FDXVHV DQ LQILQLWHYDOXH DSSUR[LPDWH VFRUH 7KLV VLWXDWLRQ PD\ DULVH IRU WKH QRUPDO FDVH

PAGE 65

IRU H[DPSOH VLQFH ERWK WKH XQFHQVRUHG DQG FHQVRUHG VFRUH IXQFWLRQV DUH XQERXQGHG DV X f§ 2QH UHPHG\ LQ SUDFWLFH LV WR UHSODFH DQ RFFXUUHQFH RI ZLWK D YDOXH RI IRU LQVWDQFH EXW WKLV LV D YHU\ VXEMHFWLYH GHYLFH WKDW FDQ FDXVH FRQVLGHUDEOH GLIIHUHQFH LQ YDOXHV RI WKH DSSUR[LPDWH VFRUHV +DUULQJWRQ DQG )OHPLQJ f HPSOR\ Ir1[f Q ;@f; ^5M a f 5M n ZKLFK WDNHV RQ YDOXHV LQ WKH LQWHUYDO @ %RWK f DQG f VWULFWO\ WDNH RQ YDOXHV LQ WKH LQWHUYDO f $OVR f FDQ EH UHJDUGHG DV D JHQHUDOL]DWLRQ IRU WKH YDOXH L 1 ? WKDW LV DOZD\V XVHG LQ WKH OLWHUDWXUH IRU DSSUR[LPDWH VFRUHV RQ XQFHQVRUHG GDWD 6R )S LV WKH HVWLPDWRU RI FKRLFH LQ SUDFWLFH IRU WKLV PDQXVFULSW 7KHRUHP EHORZ LV D PRGLILHG VWDWHPHQW RI 7KHRUHPV DQG RI &X]LFN f 7KH WKHRUHP SURYLGHV XV ZLWK D VHW RI VXIILFLHQW FRQGLWLRQV IRU WKH GLIIHUHQFH EHWZHHQ Y EDVHG RQ WKH DSSUR[LPDWH IXQFWLRQ VFRUHV DQG Y EDVHG RQ WKH H[SHFWHG VFRUHV WR EH QHJOLJLEOH LQ WKH OLPLW DV 1 f§r RR 7KH VXIILFLHQW FRQGLWLRQV DUH IDLUO\ PLOG WKH VFRUHV WKDW PDNH XS VRPH RI WKH ZHOO NQRZQ OLQHDU UDQN VWDWLVWLFV VXFK DV WKH ORJUDQN 3HWR  3HWR DQG +DUULQJWRQ t )OHPLQJfV f *S S FODVV VDWLVI\ WKHP &X]LFN f 7+(25(0 $VVXPH WKH IROORZLQJ FRQGLWLRQV RQ WKH VFRUH IXQFWLRQ IXf &O 7KH XQFHQVRUHG VFRUH IXQFWLRQ I!Xf LV WZLFH FRQWLQXRXVO\ GLIIHUHQn WLDEOH RQ f ZLWK ILUVW DQG VHFRQG GHULYDWLYHV DQG

PAGE 66

& 4 _XAnXf_ ?XI!Xf? f§ IRU VRPH D DQG % RR XD & OLP 1?DU f§cf 77LHQ LLH VFRUHV F DQG &^ LQ f t f FRQYHUJH LQ SUREDELOLW\ WR I!^ f§ )[ff DQG f§ )[ff DV 1 f§\ RR UHVSHFWLYHO\ )[f FDQ EH HLWKHU f f RU f 3URRI 5HIHU WR 7KHRUHPV DQG RI &X]LFN f 7KH IDFW WKDW I!Xf FDQ EH GLIIHUHQWLDWHG WZLFH ZLWK FRQWLQXLW\ PDLQWDLQHG ZLOO LPSO\ WKH VDPH SURSHUWLHV IRU !Xf IURP /HPPD ’ 7KH JHQHUDO IRUPV RI WKH GHULYDWLYHV RI I!Xf DUH PHVV\ VR WKDW WKH VFRUH IXQFWLRQV IRU VSHFLILF GLVWULEXWLRQDO FKRLFHV PXVW EH FKHFNHG WR VHH LI &O DQG & DUH VDWLVILHG 7KH QRQYDQLVKLQJ &RQGLWLRQ & RQ WKH YDULDQFH ZLOO IROORZ IURP WKH VWUXFWXUH REWDLQHG ZKHQ DV\PSWRWLF SURSHUWLHV RI Y DUH HVWDEOLVKHG LQ 6HFWLRQ &X]LFN 7KHRUHP f LQGLFDWHV WKDW & LV VDWLVILHG IRU VXFK D VWUXFWXUH RI WKH YDULDQFH *LOOfV &RQGLWLRQV 7KHRUHP EULQJV XV WR WKH SRLQW ZKHUH WKH PDUWLQJDOHEDVHG UHVXOWV RI *LOO f FDQ EH XVHG WR HVWDEOLVK DQ DV\PSWRWLF YDULDQFH IRU X DV ZHOO DV QRUPDOLW\ XQGHU WKH QXOO K\SRWKHVLV RI HTXDO VXUYLYDO IXQFWLRQVf IRU LWV DV\PSWRWLF GLVWULEXn WLRQ 7KH XVXDO UDQGRP FHQVRUVKLS PRGHO FI 6HFWLRQ f LV DVVXPHG

PAGE 67

7KH VWRFKDVWLF LQWHJUDO IRUP IRU Y LQ f FDQ DOVR EH FRQVLGHUHG LQ WKH IRUP GM?I L DUf $IR]f_ f ZKHUH LV D ZHLJKW IXQFWLRQ LQ WKH FODVV RI *LOO f *LOO f GHILQHV PHPEHUV f DV D IXQFWLRQ RI WKH REVHUYDWLRQV WKDW HTXDOV ]HUR ZKHQHYHU PLQ\[f 9[ff 7KH SDSHU RI $QGHUVHQ %RUJDQ *LOO DQG .HLGLQJ f VKRZV WKDW WKH FODVV RI VWDWLVWLFV IURP 3UHQWLFH f WKDW XVHV WKH )S HVWLPDWRU FDQ EH ZULWWHQ DV D VWRFKDVWLF LQWHJUDO RI WKH IRUP f ZLWK .[f DV LQ f 0RUHRYHU WKH 3UHQWLFH f FODVV LV D VXEVHW RI WKH 3UHQWLFH DQG 0DUHN f FODVV EDVHG RQ WKH XSUHVHUYDOLrQ RI VFRUHVf FRQGLWLRQ DW RXU f 7KH 3UHQWLFH DQG 0DUHN f FODVV FDQ OLNHZLVH EH ZULWWHQ LQ WKH IUDPHZRUN RI f DQG f *LOO S f SURYLGHV WKUHH FRQGLWLRQV WKDW DUH VXIILFLHQW IRU WKH DV\PSWRWLF QRUPDOLW\ RI WHVW VWDWLVWLFV RI WKH VWRFKDVWLF LQWHJUDO IRUP f 7KHVH VXIILFLHQW FRQGLWLRQV FDQ EH DSSOLHG ZLWK PDQ\ GLVWULEXWLRQDO IRUPV IRU WKH VXUYLYDO DQG FHQVRUn LQJ YDULDEOHV DQG DQ\ WHVW VWDWLVWLFV ZLWK ZHLJKW IXQFWLRQV .[f WKDW DUH PHPEHUV RI WKH JHQHUDO FODVV & :H VWDWH *LOOfV f FRQGLWLRQV DV WKH\ DUH UHOHYDQW WR RXU FDVH XQGHU WKH QXOO K\SRWKHVLV /HW -r EH WKH VHW ZLWK PHPEHUVKLS .[f Z[f 9R[f<[f <[f
PAGE 68

ZKHUH )^[f )[f ‘ /[f )L^[f *[f/[[f /HW $U[fU EH WKH FXPXODWLYH KD]DUG IXQFWLRQV DVVRFLDWHG ZLWK WKH FRQWURO DQG WUHDWPHQW JURXSV UHVSHFWLYHO\ )RU U D $U[f LV ILQLWH RQ ;r E .[f,
PAGE 69

:KHQ FRQGLWLRQV ,, DQG ,,, KROG WZR FRQVLVWHQW HVWLPDWRUV IRU WKH YDULDQFH RI Y DUH 9L >W[fO G0U[f >.;f\L[fU[f G0?^[f :S[ff \[f U[f G^0?^[f 9nR[ff f 7KH YDULDQFH HVWLPDWRUV DW f DQG f DUH VXJJHVWHG E\ *LOO S f /HPPD RI *LOO f HVWDEOLVKHV WKDW ERWK f DQG f DUH FRQVLVWHQW HVWLPDWRUV XQGHU +R IRU WKH WUXH OLPLWLQJ YDULDQFH RI X EDVHG RQ WKH IRUP f *LOO f QRWHV WKDW WKHUH LV QR WUXH RUGLQDO UHODWLRQVKLS EHWZHHQ 9? DQG 9 DQG ZH ZRXOG H[SHFW WKHP WR EH IDLUO\ HTXDO LQ SUDFWLFH IRU ODUJH VDPSOHV )RU WKH QXOO K\SRWKHVLV FDVH WKHUH LV VRPH FUHHGHQFH WR FKRRVLQJ 9 RQ WKH EDVLV WKDW LW XWLOL]HV ERWK VDPSOHV WR JHW D SRROHGW\SH RI HVWLPDWRU RI WKH FRPPRQ FXPXODWLYH KD]DUG IXQFWLRQ $[f ,Q RUGHU WR YHULI\ WKH WKUHH FRQGLWLRQV RI *LOO f DQG WKXV REWDLQ YDULDQFH H[SUHVVLRQV DQG DV\PSWRWLF QRUPDOLW\ RI L ZH FRQVLGHU VRPH PDWKHPDWLFDO UHVXOWV /(00$ $ FRQWLQXRXV IXQFWLRQ SUHVHUYHV XQLIRUP FRQYHUJHQFHf /HW ^I1^[f` EH D VHTXHQFH RI UDQGRP IXQFWLRQV WKDW FRQYHUJHV XQLIRUPO\ LQ SUREn DELOLW\ WR I[f DV 1 f§ RR IRU [ e VRPH VHW ( ,I Jf LV D FRQWLQXRXV IXQFWLRQ RQ WKH UDQJH RI ^Q[f` WKHQ AA[ff LV XQLIRUPO\ FRQYHUJHQW LQ SUREDELOLW\ WR JIL[ff DV 1 f§r RR IRU [ ( (

PAGE 70

3URRI :H NQRZ WKDW IRU DUELWUDU\ 3UVXS ?Q[f f§ I[f? f f§r‘ DV 1 f§ RR [e( /HW H EH JLYHQ 6LQFH Jf LV FRQWLQXRXV ZH FDQ ILQG VXFK WKDW _MY[ff f§ JI^[ff? W LI _Y[f f§ I[f? r!f 7KXV IRU DUELWUDU\ H 3U^VXS?JI1[ffJ^I[ff?! Hf O 3U^VQS ?JI1[ff JI^[ff? Hf [e( [e( 3UVXS ?IX[f [f_ f U ( 3UVXS _A[f [f_ f [ t( f§ DV 1 f§ RR ’ /(00$ /HW ^$A[f` EH D VHTXHQFH RI UDQGRP IXQFWLRQV WKDW LV XQLIRUPO\ FRQYHUJHQW WR $[f LQ SUREDELOLW\ DV 1 f§ RR /HW ^%A[f` DOVR EH D VHTXHQFH RI UDQGRP IXQFWLRQV WKDW XQLIRUPO\ FRQYHUJHV WR %[f LQ SUREDELOLW\ DV 1 f§rf RR $VVXPH WKDW $[f DQG %^[f DUH ERXQGHG IRU DOO [ ( 7KHQ $Q[f%cY[f FRQYHUJHV XQLIRUPO\ LQ SUREDELOLW\ WR $[f%[f DV 1 f§ RR 3URRI /HW F F 7KHQ 3UVXS _/Y[f $[ff%Q[f [ff_ Hf [e( 3UVXS _$Y[f $[ff%A[f L"[ff_ H VXS _%1[f %^[f? HFf [f( [&( 3UVXS _$DW[f $[ff%Q[f "[ff_ HVXS _eY[f -"[f_ HFf [( [e( 3UVXS _\MY[f f§ $[ff_ Ff [e(

PAGE 71

3UVXS _DW[f f§ %[f_ FFf [t( f§! f 7KH ERXQGHGQHVV FRQGLWLRQ LPSOLHV WKDW _$[f_ 0 IRU VRPH SRVLWLYH QXPEHU 0 RR ,W LV DOVR DVVXPHG WKDW 3UVXS _A[f %^[f_ !ccWf f§! [H( 0 &RPELQLQJ WKHVH ODVW WZR IDFWV ZLWK WKH UHODWLRQ 3UVXS _$[f>%\Y[f [f@_ Hf 3UVXS ?%1[f [f_ Af [( []( 0 LPSOLHV WKH UHVXOW 3UVXS _$[f>MDW[f [f@_ Hf f§r‘ f [e( DV M9 f§A RR &RPPXWLQJ WKH UROHV RI WKH WZR VHTXHQFHV ^MMY[f` DQG ^L"MY[f` VLPLODUO\ JLYHV 3UVXS _e[f>MMY[f $[f@_ Wf f§A f [e( 1H[W HPSOR\ WKH LGHQWLW\ $K[f%K[f f§ $[f%[f $Q[f $[ff%Q[f %^[ff $[f%Q[f %[ff %[f$Q[f $[ff DORQJ ZLWK ff§f WR JLYH 3UVXS _OMY[fM%A[f f§ $[fe"[f_ Hf [e(

PAGE 72

3UVXS _>$Y[f $[f@>"MY[f 6[f@_ _f [e( 2 3UVXS _>MY[f $[f@%[f? [e( 3UVXS _$[f>A[f e[f@_ -f [e( f§ DV L9 RR ZKLFK LV WKH GHVLUHG UHVXOW ’ $V\PSWRWLF 1RUPDOLW\ RI Y 5HFDOO WKDW 7KHRUHP SURYLGHV D VHW RI VXIILFLHQW FRQGLWLRQV ZKHUHE\ WKH H[SHFWHG VFRUHV LQ WKH FHQVRUHG GDWD UDQN VWDWLVWLF Y FDQ EH UHSODFHG E\ DSSUR[n LPDWH VFRUHV IRU ODUJH VDPSOHV 7KH WHVW VWDWLVWLFV FRQVLGHUHG E\ *LOO f LQ HVWDEOLVKLQJ DV\PSWRWLF SURSHUWLHV FDQ DOO EH UHJDUGHG DV FHQVRUHG GDWD OLQHDU UDQN VWDWLVWLFV EDVHG RQ DSSUR[LPDWH VFRUHV 7KHUHIRUH LQ WKH GHYHORSPHQW RI DV\PSWRWLF SURSHUWLHV IRU Y WKDW IROORZV ZH ZLOO FRQVLGHU WKH YHUVLRQ RI Y WKDW LV EDVHG RQ WKH DSSUR[LPDWH VFRUHV LH N Y f Arff a +[Lfff L L 8QGHU WKH FRQGLWLRQV RI 7KHRUHP WKH VDPH SURSHUWLHV IRU Y EDVHG RQ WKH H[SHFWHG VFRUHV DV LQ ff ZLOO IROORZ

PAGE 73

9HULI\LQJ WKH &RQGLWLRQV *LOO f XVHG WKH ORJUDQN VWDWLVWLF DV D SURPLQHQW PHPEHU RI WKH FODVV & $PRQJ WKH PDQ\ SURSHUWLHV KH H[SORUHG IRU WKLV PHPEHU KH VKRZHG WKH PHHWLQJ RI WKH WKUHH FRQGLWLRQV OLVWHG RQ SDJH RI 6HFWLRQ WKDW DUH VXIILFLHQW IRU D OLPLWLQJ QRUPDO GLVWULEXWLRQ RI WKH SURSHUO\ VWDQGDUGL]HG YHUVLRQ RI WKH VWDWLVWLF XQGHU WKH QXOO K\SRWKHVLV RI HTXDO VXUYLYDO GLVWULEXWLRQV ,Q WKH IRUP f IRU L VHWWLQJ Z[f JLYHV WKH ORJUDQN VWDWLVWLF 7KH FRUUHVSRQGLQJ ZHLJKW IXQFWLRQ LQ WKH FODVV & LV ,F[f <[f<[f \T[f \[ff ,I ZH PXOWLSO\ ,?F[f E\ WKH ZHLJKW IXQFWLRQ f )n)rff $f ))n3[ff $f )!)[fff ))!)[fff f IRU RXU PRGHO DW f ZH JHW D ZHLJKW IXQFWLRQ .[f WKDW LV D PHPEHU RI *LOOfV f FODVV & 7KH FRUUHVSRQGLQJ IXQFWLRQ Z LV UDQGRP VLQFH LW LV D IXQFWLRQ RI WKH DSSUR[LPDWH VFRUHV f§ )f DQG I!O f§ )f 1RWH WKDW Z[f DW f LV QRW UDQGRP DV LW LV D IXQFWLRQ RI WKH F DQG & &RQYHUJHQFH SURSHUWLHV DVVRFLDWHG ZLWK Z[f DW f LQ FRPELQDWLRQ ZLWK UHVXOWV DOUHDG\ ZHOOHVWDEOLVKHG *LOO f IRU WKH ORJUDQN VWDWLVWLF ZLOO SURYLGH WKH FRXUVH IRU YHULI\LQJ WKH WKUHH FRQGLWLRQV WKDW DUH VXIILFLHQW IRU DV\PSWRWLF QRUPDOLW\ RI X /(00$ 6XSSRVH WKDW IW $f $ DQG IWf IW f DUH FRQWLQXRXV GHQVLWLHV ZLWK VXSSRUW RYHU WKH LQWHUYDO f§f ,I $L DQG DUH

PAGE 74

SRVLWLYH FRQVWDQWV VXFK WKDW OLP If $X rf OLP A f} mf WKHQ Z[f GHILQHG DW f LV ERXQGHG RQ WKH LQWHUYDO f§f 3URRI %\ /f+RSLWDOfV UXOH OLPAO L )Wf OLP AaUa m! f 7KHUHIRUH OLP Wf§!RR r $f rf $f @ P OLP Wf§ I[ ‘ $f IL[f $L f§ $? f§ OLP Wf§RR IMW $f Z $OVR OLP Wf§f§RR IMW ‘‘ $f rf r;r$f@ r‘f OLP f§ f§ 22 IMW $f f f§ OLP f§ f§ 22 rfr $f $ f§ 1RZ VLQFH $f )I $f f ILWf )LWf LV FRQWLQXRXV WKHQ IRU DQ\ ILQLWH YDOXHV D WKH IXQFWLRQ f LV ERXQGHG RQ HYHU\ ILQLWH LQWHUYDO >D E` 6LQFH f LV ILQLWH DW WKH SRLQWV f§ DQG WKH VXEVWLWXWLRQ W ) )[ff VKRZV WKDW Z[f DW f LV ERXQGHG RQ f§f ’ 7KH YDOXH RI WKH /HPPD ZLOO EH VHHQ ZKHQ ZH FKRRVH VSHFLILF IRUPV IRU )[ $f EXW LW VKRXOG EH QRWHG WKDW LW GRHV QRW FRYHU WKH FDVH ZKHUH ERWK WKH

PAGE 75

FHQVRUHG DQG XQFHQVRUHG VFRUH IXQFWLRQV WHQG WR LQILQLW\ DV [ WHQGV WR LQILQLW\ )RU WKLV FDVH WKH fLQGHWHUPLQDWHf IRUP RR f§ RR IRU WKH fOLPLWf RI Z[f UHTXLUHV VSHFLDO KDQGOLQJ $Q H[DPSOH RI WKLV RFFXUV LQ &KDSWHU )RXU 7+(25(0 8QLIRUP FRQYHUJHQFH LQ SUREDELOLW\ RI WKH .DSODQ0HLHU HVWLn PDWRUf $VVXPH WKH PRGHO RXWOLQHG LQ 6HFWLRQ ZLWK WKH VXSSRUW RI *[f WR EH f§f /HW V e f§f EH VXFK WKDW WKH ULVN VHW VL]H Uf UVf \Lf f 7KHQ XQGHU WKH QXOO K\SRWKHVLV RI )^[f *[f IRU DOO [ WKH .DSODQ0HLHU HVWLPDn WRU )NP FRQYHUJHV XQLIRUPO\ RQ [ e >f§ V@ LQ SUREDELOLW\ WR ) DV 1 f§rf 7KDW LV VXS f§RR[V )NP[f )[f 3URRI 6HH 7KHRUHP RI *LOO f ZKR SURYHV D PRUH JHQHUDO FDVH +LV QRWDWLRQ XVHV )[f IRU WKH FXPXODWLYH GLVWULEXWLRQ IXQFWLRQ 7KH UHODWLRQ f ZKLFK LV JLYHQ DV &RQGLWLRQ ,F RI *LOO f KDV WKH LQWHUSUHWDWLRQ WKDW WKH VL]H RI WKH ULVN VHW DW DQ\ SRLQW [ JURZV WR LQILQLW\ DV 1 f§ ’ ,I WKH VXSSRUW RI WKH FHQVRULQJ GLVWULEXWLRQV LV DOVR f§f WKHQ V 6RPHWLPHV KRZHYHU FHQVRULQJ GLVWULEXWLRQV DUH DVVXPHG WR KDYH VXSSRUW RI WKH IRUP f§ Vf ZKHUH V DQG H[DPSOHV FDQ EH FRQVWUXFWHG WR VKRZ WKDW WKH XQLIRUP FRQYHUJHQFH RI ).0 IDLOV IRU [ V &252//$5< 7KHRUHP KROGV IRU )K0[f UHSODFHG E\ HLWKHU )S[f RU )$^[f

PAGE 76

3URRI 7KH FDVH IRU )$ LV DOVR FRYHUHG LQ *LOOfV f 7KHRUHP )RU WKH HVWLPDWRU )S ILUVW FRQVLGHU WKH IROORZLQJ UHODWLRQ IURP WKH ORQH OHPPD RI &X]LFN f )S^[f).0[f )S[f <^[ff f 7KHQ VXS f§ RR [V )S[f)^[f VXS f§RR[V VXS f§ ; )S^[f )NP^[f )NP[f )[f_ )S[f )NP[f VXS f§RR [D )NP[f)[f VLQFH VXS f§ ; )NP[f )[f? E\ 7KHRUHP DQG VXS )S^[f )NP[f VXS )3[f ‘ I rRU f§RR[m <[f LQI <[f f§ 22 ; E\ f DQG f ’ 8VLQJ WKHVH ODVW WZR UHVXOWV ZH QRZ FRQVLGHU D NH\ SURSHUW\ IRU WKH ZHLJKW IXQFWLRQ Z>[f DW f 7+(25(0 $VVXPH WKH FRQGLWLRQV RI 7KHRUHP DQG /HPPD 7KHQ WKH ZHLJKW IXQFWLRQ Z[f UHSUHVHQWHG E\ f LV ERXQGHG DQG Z FRQYHUJHV

PAGE 77

XQLIRUPO\ LQ SUREDELOLW\ WR Zr RQ f§f DV 1 f§} ZKHUH I[ $f )^[ $f I[f )^[f f 3URRI 6LQFH )[f LV DVVXPHG FRQWLQXRXV LWV LQYHUVH IXQFWLRQ ) r[f LV DOVR FRQn WLQXRXV 7KH IXQFWLRQ I)?f $f ))nf$f I)anff ))+ff f ZLOO DOVR EH FRQWLQXRXV VLQFH LW LV D FRPSRVLWH IXQFWLRQ RI FRQWLQXRXV IXQFWLRQV 7KH VXUYLYDO IXQFWLRQ HVWLPDWRU ) WDNHV RQ YDOXHV LQ WKH LQWHUYDO >@ VR /HPPD LQVXUHV WKDW L[f LV ERXQGHG ZKHQ LW LV GHILQHG RQ WKH H[WHQGHG OLQH >f§ @ $SSO\LQJ /HPPD ZLWK f LQ WKH UROH RI WKH FRQWLQXRXV IXQFWLRQ DQG )[f DV WKH DUJXPHQW ZKHUH ) KDV WKH XQLIRUP FRQYHUJHQFH SURSHUWLHV LQ 7KHRUHP DQG &RUROODU\ SURYHV WKH XQLIRUP FRQYHUJHQFH RI Zf ’ $V PHQWLRQHG SUHYLRXVO\ WKH WKUHH FRQGLWLRQV RI *LOO f KDYH EHHQ GLVFXVVHG DQG YHULILHG IRU WKH PHPEHU .F[f ZKLFK FRUUHVSRQGV WR WKH ORJUDQN VWDWLVWLF $FWXDOO\ *LOO f DWWDFKHV D VWDQGDUGL]DWLRQ IDFWRU RQ WR WKH ZHLJKW IXQFWLRQ DW f WR JHW ,&F[f 1S1L <[f<[f 1 1L f 1 $UL 1R 1U U[f )L[f 7KH PXOWLSOLFDWLYH IDFWRU LV DWWDFKHG WR HQVXUH WKDW WKH YDULDQFH RI WKH WHVW VWDWLVWLF FRUUHVSRQGLQJ WR .T[f LV ERXQGHG DZD\ IURP DQG DV 1 f§!f 1RWH WKDW WKLV SURYLGHV D WHVW VWDWLVWLF Yr 1S 1U 11U

PAGE 78

ZKHUH Y UHPDLQV GHILQHG DV LQ f DQG f 7KH YDULDQFH HVWLPDWRUV 9? DQG 9 UHVSHFWLYHO\ JLYHQ E\ f DQG f FDQ EH DGMXVWHG DFFRUGLQJO\ DQG WKHLU FRQVLVWHQF\ IRU WKH YDULDQFH RI Yr LV HVWDEOLVKHG LQ /HPPD RI *LOO f 7KDW OHPPD LV D SUHFXUVRU WR *LOOfV f &RUROODU\ DQG 3URSRVLWLRQ ZKLFK VSHFLI\ WKH DV\PSWRWLF GLVWULEXWLRQ IRU WKH WHVW VWDWLVWLF EDVHG RQ .T[f 7KH VWDQGDUGL]DWLRQ IDFWRU RI *LOO f LV VSHFLILFDOO\ “A7. 9 $: n 7KH SUHYLRXV SDUDJUDSK GHILQHG WKH UHODWLRQVKLS EHWZHHQ Y DQG Yr 6XSSRVH WKHUH H[LVWV D YDULDQFH RI Lr 9DULrf VXFK WKDW Yr ?-9DULrf LV D UDQGRP YDULDEOH ZLWK VRPH DV\PSWRWLF GLVWULEXWLRQ $OVR VXSSRVH WKDW WKH YDULDQFH HVWLPDWRUV 9L DQG 9 DUH VXFK WKDW 1 1 Y 11[ 1R 1A 1 1[ DUH FRQVLVWHQW HVWLPDWRUV RI 9DULrf %\ 6OXWVN\W\SH DUJXPHQWV DQG 7Y fG 7: \-9D[Yf ZLOO KDYH WKH VDPH DV\PSWRWLF GLVWULEXWLRQ %XW QRWH WKDW 9r 9 DQG

PAGE 79

VR WKHUH DUH QXPHURXV H[SUHVVLRQV RI UDQGRP YDULDEOHV WKDW DUH DV\PSWRWLFDOO\ HTXDO LQ GLVWULEXWLRQ 7KH SURRIV DQG VXUURXQGLQJ GLVFXVVLRQV RI *LOOfV f &RUROODU\ DQG 3URSRVLWLRQ QRWH WKDW VXS f§RR[RR SR)R[f SL)A[f G$^[f f 5HFDOO WKH PL[WXUH PRGHO DW f 8QGHU WKH QXOO K\SRWKHVLV LU !Ym0

PAGE 80

FRQYHUJHV LQ GLVWULEXWLRQ WR D VWDQGDUG QRUPDO UDQGRP YDULDEOH DV 1 f§ RR )XUn WKHUPRUH ERWK HVWLPDWRUV \Df U[ffM GM9[f $UL[ff ZLOO EH VXFK WKDW 1R 1L 7 1 1X 9? DQG f§f§f§f§f§Y 11M 11 FRQYHUJH LQ SUREDELOLW\ WR 9DUMrf DV 1 RR 3URRI 8QGHU WKH QXOO K\SRWKHVLV U DQG WKH UDQGRP FHQVRUVKLS PRGHO RXWOLQHG LQ 6HFWLRQ &RQGLWLRQV f DQG f DUH VXIILFLHQW IRU FRQGLWLRQV ,f§,,, WR KROG IRU .F[f :H VWDUW ZLWK YHULILFDWLRQ RI &RQGLWLRQ OD )RU WKRVH YDOXHV RI [ LQ -r VXFK WKDW PLQ)R[f )L[ff ERWK )[f DQG *[f 7KXV WKH FRUUHVSRQGLQJ FXPXODWLYH KD]DUG IXQFWLRQV ZLOO EH OHVV WKDQ LQILQLW\ LH ILQLWH RQ ,Q &RQGLWLRQ OE OHW .^[ff§f DV 1 f§ 7KH XQLIRUP FRQYHUJHQFH ZLOO KROG RQ FORVHG VXELQWHUYDOV RI -r DV ZHOO $SSO\LQJ /HPPD ZLWK $Y[f Z[f

PAGE 81

DQG %Q[f ,F[f JLYHV .[ff§@ -,KU[fG$U[f ` K"[fG$U[f 0L f [fG$U[f -Lr DQG WKHUHIRUH

PAGE 82

VR WKDW &RQGLWLRQ ,OD ZRXOG EH VDWLVILHG LI 6 e 7r VLQFH LI [fG$U[f RR -L ZDV HVWDEOLVKHG IRU WKH ORJUDQN VWDWLVWLF LQ *LOO f $QDORJRXVO\ WKHUH LV D SRVLWLYH QXPEHU 0 VXFK WKDW Z[f 0 VR &RQGLWLRQ OLE IROORZV IURP OLPOLPVXS3U > .[f<7[fG$U[f Hf [@6 Zf§RR -[ OLPOLPVXS3U > 0.T [f<7[fG$7[f Hf U6 ARR -[ OLPOLPVXS3U$I > .J [f
PAGE 83

&252//$5< 8QGHU WKH FRQGLWLRQV RI 7KHRUHP DQG 99c FRQYHUJH LQ GLVWULEXWLRQ WR D VWDQGDUG QRUPDO YDULDEOH DV 1 f§ RR 3URRI 5HFDOO WKDW L 1r 1LY Q L R LQ WKH GLVFXVVLRQ EHIRUH 7KHRUHP DQG DSSO\ D 6OXWVN\W\SH DUJXPHQW ’ 7KH H[SUHVVLRQV JLYHQ LQ &RUROODU\ DUH PRVW FRQYHQLHQW IRU FDOFXODWLQJ WKH VWDWLVWLF RQ GDWD ,I WKH VXSSRUW RI WKH VXUYLYDO DQG FHQVRULQJ YDULDEOHV LV f§ f WKHQ 6 DQG &RQGLWLRQ ,,, ZLOO WKHQ EH HPSW\ 7KLV LV DOVR WUXH LI QR FHQVRULQJ RFFXUV 2Q WKH RWKHU KDQG LW LV RIWHQ WHQDEOH LQ SUDFWLFH WR DVVXPH XQLIRUPO\ GLVWULEXWHG FHQVRULQJ WLPHV ZLWK ILQLWH VXSSRUW ,Q WKLV FDVH &RQGLWLRQ ,,, LV UHTXLUHG DV 6 8VH RI WKH 7HVW %DFN LQ 6HFWLRQ WKH PL[WXUH PRGHO f ZDV LQWURGXFHG ZLWK WKH SUHn VXPSWLRQ WKDW $ LH WKDW ODUJHU YDOXHV RI WKH UHVSRQVH ZHUH DVVRFLDWHG ZLWK WKH WUHDWPHQW JURXS 6HH $VVXPSWLRQ $f 7KH DV\PSWRWLF QRUPDO GLVWULEXWLRQ RI WKH WHVW VWDWLVWLF GHYHORSHG LQ 7KHRUHP VXJJHVWV WKDW WKH RSSRVLWH VLWXDWLRQ RI VPDOOHU YDOXHV $ f FDQ EH KDQGOHG DV ZHOO DV ORQJ DV WKH UHTXLUHG FRQGLWLRQV KROG 1RWH WKDW WKH VSHFLDO FDVH RI 7KHRUHP LV LQFOXGHG KHUH ,I D WHVW DJDLQVW WKH DOWHUQDWLYH *[f )^[f ZLWK VWULFW LQHTXDOLW\ IRU DW OHDVW RQH [

PAGE 84

LV GHVLUHG WKH UHMHFWLRQ UHJLRQ ZLOO EH LQ WKH ORZHU WDLO RI WKH VWDQGDUG QRUPDO GLVWULEXWLRQ )RU $ WKH XSSHU WDLO LV DSSURSULDWH $EVHQFH RI DQ\ NQRZOHGJH DERXW $ VKRXOG KDYH D UHMHFWLRQ UHJLRQ LQYROYLQJ ERWK WDLOV ,W LV QRW WUXH KRZHYHU WKDW X RU WKH WHVW VWDWLVWLF WKDW LV D VWDQGDUGL]HG YHUVLRQ RI Y LV DQ RGG RU HYHQ IXQFWLRQ RI $ 7KH IDFW WKDW Y LV QRW D V\PPHWULF IXQFWLRQ RI $ JLYHV DQRWKHU DVSHFW LQ WKH FRQVLGHUDWLRQ RI WKH FKRLFH RI $ IRU FRQGXFWLQJ WKH WHVW +RZHYHU N < F UULL&Lf f L L KROGV VLQFH WKH VXP f LV WKH DYHUDJH RI VXPV RI VFRUHV WKDW RFFXU IURP DOO SRVVLEOH XQGHUO\LQJ UDQN YHFWRUV JLYHQ WKH GDWD 3UHQWLFH f 1RWH WKDW f LPSOLHV N N 9 < }f} 0L&Lf < a RfFm Pmf a 0Lf&Lf f L L L L +HQFH VXPPDWLRQ RI WKH VFRUHV DVVLJQHG WR WKH FRQWURO JURXS REVHUYDWLRQV ZKHQ $ LV HPSOR\HGf SURGXFHV D VPDOO YDOXH IRU DQ DSSURSULDWHO\ VWDQGDUGL]HG WHVW VWDWLVWLF WKDW FRXOG EH FRPSDUHG ZLWK WKH ORZHU WDLO RI WKH VWDQGDUG QRUPDO GLVWULn EXWLRQ ,I ODUJHU YDOXHV IRU WKH FRQWURO JURXS DUH SUHVHQW WKH DVVLJQHG VFRUHV IRU WKH FRQWURO JURXS ZLOO OLNHZLVH WHQG WR EH ODUJHU WKDQ WKRVH VFRUHV IRU WKH WUHDWPHQW JURXS 7KHQ Y FI f EDVHG RQ WKH WUHDWPHQW JURXS VFRUHV ZLWK $ ZLOO WHQG WR EH VPDOO DQG WKH WHVW VWDWLVWLF LQ 7KHRUHP VKRXOG EH FRPSDUHG ZLWK WKH ORZHU WDLO RI WKH VWDQGDUG QRUPDO GLVWULEXWLRQ 6XPPLQJ WKH QHJDWLYHV RI WKH VFRUHV LQ f ZRXOG SURGXFH ODUJH YDOXHV RI WKH WHVW VWDWLVWLF EDVHG RQ L DQG

PAGE 85

WKH UHMHFWLRQ UHJLRQ VKRXOG WKHQ EH EDVHG RQ WKH XSSHU WDLO RI WKH VWDQGDUG QRUPDO GLVWULEXWLRQ 7KLV DSSURDFK ZDV VXJJHVWHG E\ &RQRYHU DQG 6DOVEXUJ f IRU WKHLU VFRUHV GHULYHG IURP /HKPDQQ DOWHUQDWLYHV DQG XQFHQVRUHG GDWD 7KHUHIRUH LI VPDOOHU YDOXHV RI WKH UHVSRQVH IRU WKH WUHDWPHQW JURXS LV RI LQWHUHVW 7KHRUHP SHUPLWV XV WR HLWKHU &KRRVH D YDOXH RI $ WR FDOFXODWH WKH VFRUHV DQG FRPSDUH Y ZLWK WKH ORZHU WDLO 7DNH WKH QHJDWLYHV RI WKH VFRUHV EDVHG RQ D $ DQG FRPSDUH Y ZLWK WKH XSSHU WDLO 7DNH WKH VFRUHV EDVHG RQ $ DQG FRPSDUH ZLWK WKH ORZHU WDLO &KRLFHV f DQG f ZLOO EH HTXLYDOHQW VLQFH WKH UHMHFWLRQ UHJLRQV DUH EDVHG RQ WKH VWDQGDUG QRUPDO GLVWULEXWLRQ 'HDOLQJ ZLWK 7LHV 7KRVH ZKR DUH SUDFWLWLRQHUV RI VWDWLVWLFV NQRZ WKDW WLHV LQ WKH REVHUYHG GDWD DUH RIWHQ SUHYDOHQW &RQWLQXLW\ DVVXPSWLRQV RQ WKH VXUYLYDO DQG FHQVRULQJ GLVWULEXWLRQV LPSO\ WKDW WKH SUREDELOLW\ RI WLHV LV ]HUR EXW PHDVXUHPHQW HUURU IRUFHV XV WR JURXS WKH GDWD DW SODXVLEOH WLPHV /HW Gf GHQRWH WKH QXPEHU RI REVHUYHG IDLOXUH WLPHV LQ WKH WUHDWPHQW JURXS DW WLPH ef DQG OHW Gf EH WKH WRWDO QXPEHU RI REVHUYHG IDLOXUH WLPHV DW [A\ 7KH WHVW VWDWLVWLF Y DV LQ f FDQ EH PRGLILHG E\ WKH XVXDO

PAGE 86

FRQYHQWLRQ HJ 3UHQWLFH DQG 0DUHN f Y ( Znf G+Lf a fAf f f 7KH VWRFKDVWLF LQWHJUDO IRUP f DOUHDG\ FRYHUV WKH PRGLILFDWLRQ DV GRHV WKH H[SUHVVLRQ f IRU WKH OLPLWLQJ YDULDQFH 1RZ GHILQH $M9U[f $IU[f f§ -?IU[f§f WR EH WKH QXPEHU RI IDLOXUH WLPHV DW [ WKDW EHORQJ WR WUHDWPHQW JURXS U U 1RWH WKDW $ LV QRW UHODWHG WR WKH SDUDPHWHU $f 7KH YDULDQFH HVWLPDWRUV DUH PRGLILHG DV URR YL  r1[f U -arr <;U[f 9 L 9 $:U[fQ O <;f GM?IU[f DQG 9 &2 Z[f RR
PAGE 87

ZLWK DQG :L ![ff f§ I![ff :KHQ WKHUH DUH QR WLHV LQ WKH REVHUYHG GDWD f UHGXFHV WR N n5X 5 e L L L 5X 5L f ([SUHVVLRQ f KDV RIWHQ EHHQ LQWHUSUHWHG LQ WKH OLWHUDWXUH DV D ZHLJKWHG VXP RI K\SHUJHRPHWULF YDULDQFHV EHFDXVH RI WKH DUJXPHQW RI 0DQWHO f LQ GHULYLQJ WKH ORJUDQN WHVW IURP D VHULHV RI LQGHSHQGHQW [ FRQWLQJHQF\ WDEOHV (YDOXDWLRQ RI ([SHFWHG 6FRUHV 7KH IRUPV RI WKH H[SHFWHG VFRUHV LQ f DQG f SURGXFH YHU\ LQYROYHG PXOWLSOH LQWHJUDWLRQV ZKHQ VRPH RI WKH PM DUH QRQ]HUR LI ZH DSSURDFK WKH HYDOXDWLRQ LQ D EUXWHIRUFH PDQQHU %XW VXSSRVH ZH DVVXPH WKDW !O f§ mfff LQ f 7KHQ WKH LQWHJUDWLRQ LV VWUDLJKWIRUZDUG 3UHQWLFH f DQG HTXDOV WKH YDOXH RI 7KLV VXJJHVWV WKDW N JPXXNf Q XL fff XN M L FRQVWLWXWHV D MRLQW GHQVLW\ LQ WKH ]TV 6LQFH WKH H[SHFWHG VFRUHV LQYROYH VFRUH IXQFn WLRQV WKDW RQO\ GHSHQG RQ D SDUWLFXODU XW WKH VFRUHV F DQG & FDQ EH UHSUHVHQWHG DV F > W!XLfJrXLfGXL@ -R f &^ XLfJrXLfGXL -R f ZKHUH fXLf f f ‘ M :B5@^ 8MfPGX[f f GXLAGXL[‘ ‘ GXN f 8O f§8N M

PAGE 88

LV WKH PDUJLQDO GHQVLW\ LQ LL FRUUHVSRQGLQJ WR WKH MRLQW GHQVLW\ JrXL XMWf ,W WXUQV RXW WKDW IRU WKH VFRUH IXQFWLRQV FRQVLGHUHG LQ WKLV GLVVHUWDWLRQ WKH LQWHJUDOV LQ f DQG f GR QRW KDYH QLFH FORVHGIRUP H[SUHVVLRQV %XW QXPHULFDO HYDOXDWLRQ RI WKH LQWHJUDOV FDQ EH FDUULHG RXW LQ D VWUDLJKWIRUZDUG PDQQHU 7KH )RUP RI JrXLf 7R JDLQ VRPH LQVLJKW FRQVLGHU WKH FDVH L ,QWHJUDWLRQ RYHU 8LQ JrXLXNf \LHOGV N JcXLf M Q ^ 8MfPMGXM` 5[O8Ufr X[ 8IFO m 7R REWDLQ AAf ZH FDQ LQWHJUDWH RXW 8 f f f 8N DQG WKHQ X[ 8  Q 8r m Xf QZLmMUbM` 8r m f Xf+B O 8OfPAG8O X A O n ` 5? f§ 5 5 f§ 5? f A VLff ‘‘‘c,-LQPf§UGXM` )RU L WKH KRXVHNHHSLQJ EHFRPHV PRUH H[WHQVLYH :H JHW 8 m I Q XN f§ O 8 f"f "OWIMIWfO a 8VfAn -^O a 8fP:O 8OfPAG8OG8 5LI"5fO f§ 8f5L 8 8

PAGE 89

[ XA/f ^O 8Amf`GXL X "" 8fr f Xf5r5aOGX 8 AA Xf 5 B5f 5c5,5OXIfn f§ " A f§ AfA 5L 5.5 "f "L "A" f§ AfA ^OOXfIOr` 5L f§ 5f5 f§ 5]f ^5? f§ 5Lf5? f§ 5f B "L f§ XfA +"L" f§ fAr " f§ 8f5V "L f§ "f f§ 5f f§ "Lf f§ Lf "" XDfr f§ f f§ "f "" f§ 8Vf5 "L f§ f" f§ "f f§ Lf" f§ "Lf $ UHDVRQDEOH FRQMHFWXUH WKHQ IRU DUELWUDU\  LQ f LV mffmf IO ‹ f Y Q 5L 5Mf : 7KH YDOLGLW\ RI f FDQ EH SURYHQ E\ PDWKHPDWLFDO LQGXFWLRQ :H VWDUW ZLWK D UHVXOW WKDW ZLOO EH XVHG LQ WKH SURRI

PAGE 90

/(00$ 7KH ULVN VHW VL]HV 5L L N 5NL f VDWLVI\ f§ f§f§ L LN K^5L 5Wf Q55Mf n 3URRI 7KH SURGXFW WHUP LQ WKH GHQRPLQDWRU RI WKH OHIW KDQG VLGH FDQ EH UHJDUGHG DV D SRO\QRPLDO LQ I"L ZLWK WKH VLPSOH URRWV 5[ 5 5L 7KHQ WKH ZKROH H[SUHVVLRQ RQ WKH OHIW KDQG VLGH LV D UDWLR RI WZR UDWLRQDO IXQFWLRQV 6LQFH WKH GHQRPLQDWRU LV D SRO\QRPLDO ZH FDQ GHFRPSRVH LW LQWR PRUH HOHPHQWDU\ IXQFWLRQV WKDW LQYROYH WKH IDFWRUHG WHUPV $ GLVFXVVLRQ RI WKH WHFKQLTXH FDQ EH IRXQG LQ *UDGVKWH\Q t 5K\]LN S f 7KH IROORZLQJ QRWDWLRQV RI DQG M! PLPLFV WKHLUV DQG LV WR EH DVVXPHG RQO\ LQ WKH ORFDO FRQWH[W RI WKLV SURRI 'HQRWH I5f 855f< L L W!^5f DV WKH WZR UDWLRQDO IXQFWLRQV 7KHQ `!^5Lf B AL 0 $M I^5LLf 5WL f§ 5? 5WL f§ 5" 5LL f§ 5L f ZKHUH B fB c!5Mf n5[ff In5\ $ I5W\ 1RZ I^5[Lf f§ 5LL f§ 5?f5bL f§ 5f f f f 5 f§ 5Lf

PAGE 91

6R I5 WLf f§ Pr} B a ‘ ‘ ‘QrL f§ Af} L L 0O 0 0 ZKLFK LPSOLHV WKDW $IWf QWIL 0O ULIWf QZ IWf 0 P QZIWf 0r DV DOO RWKHU WHUPV GURS RXW 6LQFH I!5Lf fff" ZH KDYH .IWLf B I^5Of LW-5fQAL-5f L L 0O 5LA5L.8L5L5f 0r f L Q5L5Lf 0O f f f 85L5Lf 0} B9L mL L L 0L &RXSOHG ZLWK WKH IDFW WKDW :Lf I^5Lf frn O • f§ Lf L ZH JHW WKH GHVLUHG HTXDOLW\ ’

PAGE 92

$V D ILUVW VWHS LQ WKH LQGXFWLRQ DUJXPHQW QRWH WKDW f KROGV IRU L 1H[W DVVXPH WKDW f KROGV IRU L )URP WKLV DVVXPSWLRQ LW PXVW EH SURYHQ WKDW D YHUVLRQ RI f ZLWK L I UHSODFLQJ L HYHU\ZKHUH LV DOVR WUXH )URP WKH MRLQW GHQVLW\ LQ WKH XL Xr ZH QHHG WR LQWHJUDWH RXW X" WT FDOO WKLV fVXEUDQJH ff DQG Uf Xr fVXEUDQJH ff LQ RUGHU WR REWDLQ WKH PDUJLQDO GHQVLW\ Jn[ XLf ,QWHJUDWLRQ RYHU VXEUDQJH \LHOGV 5L XLfIB -IO 5MO 8MfPLGXM f VXEUDQJH r 7R VHH ZKDW KDSSHQV RYHU VXEUDQJH ZULWH f DV }L L Xfr KU .Ln L A Xffr!r‘ A IO5L5Mf O L OrM f 1RWH WKH VLPLODULW\ ZLWK f %HFDXVH ZH DUH DVVXPLQJ WKH FDVH IRU L LV WUXH WKH H[SUHVVLRQ m Q mfn 9Ln L AO XWf5!a5! L IO^5L 5Mf O O OrM f LQ f LV WKH YDOXH RI WKH LQWHJUDO RI JrX? 8Nf RYHU XL XBL 7KH VXEVHn TXHQW LQWHJUDWLRQ RI f RYHU X SURGXFHV n Q mLf  f§f§ R Xn! n n Q IW IWf R r ( 7 L QAAf L L r 5M f§ 5WL XLf 5M f§ 5L f

PAGE 93

7KH VXEVWLWXWLRQ RI f LQWR f JLYHV Qb 9-n 785W5Mf L L XLOf5f IO 5LL f§ 5Mf 5M f§ 5LL L Q m! :n WnO L Q b Xn O W0 a I BA WL /L L M Q 5L5Mf 85L5Mf O O L L 0L M L Q ^5L f§ 5Mf Q Uc 5LLf ? Lr@ rf f ZLWK WKH ODVW VWHS DULVLQJ IURP VXEVWLWXWLRQ RI WKH HTXDWLRQ LQ /HPPD WR JHW WKH ODVW WHUP RQ WKH ULJKW KDQG VLGH RI f &ROOHFWLQJ WKH L WHUPV LQ f LQWR RQH VXPPDWLRQ JLYHV A WL f ‘ UL5L5Mf ZKLFK LV WKH GHQVLW\ LQ XM WKDW PDWFKHV WKH IRUP f IRU X 7KLV FRPSOHWHV WKH LQGXFWLRQ DUJXPHQW WKDW f KROGV IRU DOO L $OWKRXJK WKH IRUP JfXLf LQ f LV QRW VLPSOH DQDO\WLFDO RU QXPHULFDO HYDOn XDWLRQV RI F DQG & ZLOO LQYROYH VLQJOH LQWHJUDOV 3URSHUWLHV 8QGHU +D 7KH EHKDYLRU RI WKH OLQHDU UDQN WHVW VWDWLVWLFV GHULYHG LQ SUHYLRXV VHFWLRQV FDQ EH VWXGLHG LQ WHUPV RI 3LWPDQf DV\PSWRWLF UHODWLYH HIILFLHQF\ $5(f 7KH VWUXFWXUH RI ORFDO DOWHUQDWLYHV RI SDUDPHWHU YDOXHV FRQYHUJLQJ WR WKH QXOO K\SRWKHVLV YDOXH U f§ ZLOO DOORZ XV WR FRPSDUH WKH ORFDO SRZHUV RI Y IRU GLIIHUHQW VFRUHV

PAGE 94

*LOOfV f IRXQGDWLRQDO ZRUN ZLOO DJDLQ EH DSSOLHG ,Q SDUWLFXODU KLV &KDSWHU )LYH SURYLGHV VXIILFLHQW FRQGLWLRQV IRU DV\PSWRWLF 1 f§ RRf QRUPDOLW\ IRU VWDQn GDUGL]HG Y XQGHU D VHTXHQFH RI ORFDO DOWHUQDWLYHV LQ WKH ORFDWLRQVKLIW PRGHO *LOOfV f UHVXOWV FDQ EH XVHG WR HYDOXDWHG WKH fHIILFDF\f RI WKH OLQHDU UDQN WHVW VWDWLVWLF EDVHG RQ Y DQG WKH VHTXHQFH RI ORFDO SDUDPHWHU YDOXHV 7KH 3LWPDQ $5( RI RQH WHVW ZLWK D FRPSHWLWRU FDQ EH HVWDEOLVKHG E\ HYDOXDWLQJ WKH UDWLR RI WKHLU HIILFDFLHV 7KH HIILFDFLHV LQ JHQHUDO GHSHQG RQ WKH FHQVRULQJ GLVWULEXWLRQV IRU WKH WZR VDPn SOHV 7KXV ZH FDQ VWXG\ WKH LQIOXHQFH RI FHQVRULQJ GLVWULEXWLRQV RQ EHKDYLRU RI WKH WHVWV )RU WKH H[SRQHQWLDO GLVWULEXWLRQ H[WUHPHYDOXH LQ WKH ORJDULWKPLF VFDOHf LW LV NQRZQ WKDW IL[HG QRW GHSHQGHQW RQ 1f DQG HTXDO FHQVRULQJ GLVWULEXWLRQV IRU WKH FRQWURO DQG WUHDWPHQW SRSXODWLRQV DUH VXIILFLHQW IRU WKH ORJUDQN WR EH IXOO\ HIILFLHQW &URZOH\ DQG 7KRPDV f *LOO f H[WHQGHG WKLV UHVXOW WR RWKHU GLVWULEXn WLRQDO IRUPV LQFOXGLQJ WKH ORJLVWLF GRXEOHH[SRQHQWLDO DQG QRUPDO GLVWULEXWLRQV 7KH 6WUXFWXUH RI /RFDO $OWHUQDWLYHV /HW ^A$I` GHQRWH D VHTXHQFH RI SDUDPHWHUV EHORQJLQJ WR @ ZKHUH IRU VRPH FRQVWDQW D 7KLV FKRLFH KDV EHHQ XVHG E\ DXWKRUV LQ WKH XQFHQVRUHG GDWD FDVH -RKQVRQ HW DO f :KHQ FRQYHQLHQW WKH YDOXH RI D FDQ EH DVVXPHG ZLWKRXW ORVV RI JHQHUDOLW\ 7KH VHTXHQFH RI FRUUHVSRQGLQJ FRQWURO DQG WUHDWPHQW SRSXODWLRQ VXUYLYDO IXQFWLRQV LV )1[f )[f XQFKDQJHG IURP +f

PAGE 95

*Q[f WWcY)[ $f f§ WcYf)[f &RQVLVWHQW ZLWK SUHYLRXV GHILQLWLRQV WKH UHVSHFWLYH FXPXODWLYH KD]DUG IXQFWLRQV DUH $R]f ORJ)[ff DQG $r [f ORJ*1[ff 6XIILFLHQW &RQGLWLRQV ,Q VHFWLRQV DQG RI WKLV PDQXVFULSW *LOOfV S f FRQGLWLRQV VXIILFLHQW IRU D OLPLWLQJ QXOO GLVWULEXWLRQ ZHUH VWDWHG DQG YHULILHG IRU Y LQ WKH PL[HG PRGHO DW f 8QGHU D VHTXHQFH RI ORFDO DOWHUQDWLYH SDUDPHWHU YDOXHV *LOOfV f FRQGLWLRQV RQ KLV SDJH LQ DGGLWLRQ WR WKRVH JLYHQ RQ KLV SDJH *LOO f ZLOO KDYH WR EH YHULILHG LQ RUGHU WR HVWDEOLVK DV\PSWRWLF SURSHUWLHV :H DGRSW WKH QRWDWLRQDO FRQYHQWLRQ RI *LOO f ZLWK VXLWDEOH PRGLILFDWLRQV IRU VWDWLQJ WKHVH FRQGLWLRQV 7R GHDO ZLWK ORFDO DOWHUQDWLYHV FHUWDLQ SDUWV RI WKH FRQGLWLRQV LQ RXU 6HFWLRQ PXVW EH UHSODFHG ZLWK PRUH JHQHUDO VWDWHPHQWV 7KH IROORZLQJ LV D OLVW RI *LOOfV f FRQGLWLRQV VWDWHG LQ WHUPV RI RXU PL[HG PRGHO VHWXS f 7KHUH H[LVW U[f VXFK WKDW [ 11L G? [ ? G$7Ofa 9 U ff XQLIRUPO\ RQ HDFK FORVHG VXELQWHUYDO RI ^[ )[f ` $OVR OHW [f Rrf f§ L[f .[f Z[f.T[f Z[f
PAGE 96

EH VXFK WKDW OLP OAs(L.>[f N[f 1f§[[! 9 1T1L XQLIRUPO\ LQ SUREDELOLW\ RQ FORVHG VXELQWHUYDOV RI ;f ^ [ PLQRf )L[f f ` 7KH IXQFWLRQ N[f FDOOHG D fOLPLWLQJ ZHLJKW IXQFWLRQf E\ *LOO f LV OHIW FRQWLQn XRXV ZLWK ULJKW KDQG OLPLWV VXFK WKDW N[f OLP NWf f§ LV RI ERXQGHG YDULDWLRQ RQ FORVHG VXELQWHUYDOV RI ;r 7KH IXQFWLRQ N[f LV GHILQHG WR EH ]HUR LQ UHJLRQV RXWVLGH RI ;r D )1[f FRQYHUJHV XQLIRUPO\ RQ ;r WR )[f DV 1 f§ RR *1[f FRQYHUJHV XQLIRUPO\ RQ ;r WR *[f DV 1 f§r RR $OVR $UDf OLP $A]f 1f§N[! LV ILQLWH RQ ;r E ,?[f
PAGE 97

,,r /HW 6 VXS =r ,I 6 = WKHQ IRU U D LU[f=$U[f L RR OLPOLPVXS 3U .Wf<7WfG$AWf Hf L76 1f§RR f>re@ IRU HYHU\ H ,,,r ,I 6 RR WKHQ IRU U .[f
PAGE 98

9r ,I 6 RR WKHQ IRU U FRQYHUJHV LQ SUREDELOLW\ WR DV 1 f§} RR 6RPH RI WKH FRPSRQHQWV RI ,,r DQG ,,,r DUH HVVHQWLDOO\ QR PRUH WKDQ D VXEVWLWXn WLRQ RI $A[f IRU $U[f LQ FRQGLWLRQV ,, DQG ,,, $OVR QRWH WKDW $A[f $[f $[f ,Q RUGHU WR YHULI\ ,r 9r IRU WKH PL[HG PRGHO VHWXS ZH IROORZ RXU VWDWHJ\ LQ WKH QXOO K\SRWKHVLV VLWXDWLRQ ZKHUH HDFK FRQGLWLRQ ZDV YHULILHG LQ WZR VWHSV (VWDEOLVK WKDW VXFK FRQGLWLRQV KDYH EHHQ YHULILHG E\ *LOO f IRU WKH FDVH .[f .T[f ORJUDQNf DQG 8VH f DORQJ ZLWK WKH IDFW WKDW RXU ZHLJKW IXQFWLRQ .[f FDQ EH H[SUHVVHG DV D SURGXFW RI D ERXQGHG ZHLJKW IXQFWLRQ Z[f DQG .A^[f 7KLV DSSURDFK ZLOO EH UHIHUUHG WR DV WKH fWZRSRLQWf PHFKDQLVP LQ WKH UHPDLQGHU RI WKLV VHFWLRQ ,Q WKH YHULILFDWLRQ RI ,rf§,,,r WKH FDVH U EULQJV XV EDFN WR WKH FRQGLWLRQV DOUHDG\ YHULILHG IRU WKH QXOO K\SRWKHVLV FDVH RI 6HFWLRQ 2QO\ WKH FDVH U UHPDLQV :H VWDUW ZLWK FRQGLWLRQ ,rD 7KH IXQFWLRQV *Q[f1 DQG *[f DUH FRQWLQXRXV VXUYLYDO IXQFWLRQV DQG OLP *DW[f *[f OLP *Y[f *[f IRU DOO [ 1WRR 1f§rRR

PAGE 99

'XH WR D ZHOONQRZQ UHVXOW GXH WR 3RO\D VHH HJ 6HUIOLQJ ff WKH XQLIRUP FRQYHUJHQFH LV SURYHG &RQGLWLRQ ,rE IROORZV MXVW DV FRQGLWLRQ OE GLG EHFDXVH .[f Z[f.F[f ZKHUH Z[f LV ERXQGHG 7R HYDOXDWH r\[f DQG RWKHU H[SUHVVLRQV ZH QHHG $I[f V D[ 1^[f *1[f 71[fI[ $f 771[ffI[f WQ[f)[ $f 7$UDffLUDff DQG G$[f G[ I[f )[f $[f 7KHQ 0S Vf G$RAf DQG G$ILf $I[f G$[f $[f 7Q[f[ $f UU1[ffI[f MQ[f)[ $f WWQ[ff)[f rr^[f a Of rrrf A Of 7KHUHIRUH nIR[f DQG f f§A?^[f 1RZ )^rf I[f 1 @@ 1 1L ? G$S[f

PAGE 100

OLP OLP 1 1U 1R 1U ? 1R 1U f 1R 1U 1R 1U ? 1R 1U \M1 L9M G?"[f B ? ?G?[f f [Q :%Afr 8SRQ VXEVWLWXWLQJ 7\Y ZH JHW L[f OLP 1r 1O [O I[ $f )[$f ? `[f )[f ? 1R 1U 9 1 1U ? PLf L L ?-3?3t n I[ $f )[ $fn I[f ?3L3DZr[f )[f DV 1 f§ RR ZKHUH WRr[f ZDV GHILQHG DW f LQ 7KHRUHP 7KLV ODVW FRQn YHUJHQFH LV XQLIRUP RQ HDFK FORVHG VXELQWHUYDO RI ^[ )[f ` E\ WKH VDPH UHDVRQLQJ FI f WZRSRLQW PHFKDQLVPf HPSOR\HG LQ 7KHRUHP /LNHZLVH DV LQ f 1R 1 >r $f )[$f` )[f)[f 9 1R1L >;f rf )[f n SR)^[f SO)^[f N[ff XQLIRUPO\ LQ SUREDELOLW\ RQ FORVHG VXELQWHUYDOV RI ,r ZLWK N[f EHLQJ OHIW FRQWLQXRXV ZLWK ULJKW KDQG OLPLWV DQG $[f RI ERXQGHG YDULDWLRQ DJDLQ VLQFH Z[f LV ERXQGHG DQG WKH YHUVLRQ RI WKHVH SURSHUWLHV IRU WKH ORJUDQN VWDWLVWLF KDYH EHHQ YHULILHG LQ *LOO f &RQGLWLRQ ,,rD LV WKH VDPH DV FRQGLWLRQ ,, LQ WKH QXOO K\SRWKHVLV FDVH DQG WKXV LV DOUHDG\ YHULILHG 9HULILFDWLRQ RI FRQGLWLRQV ,,rE DQG ,,,r DJDLQ PDNHV XVH RI WKH WZR SRLQW PHFKDQLVP DORQJ ZLWK /HPPD RI *LOO f DQG KLV SURRI RI 3URSRVLWLRQ $ SDLU RI LQHTXDOLWLHV ,F[f A <[f <^[f 1 1 A1 1[ <[f 7L[f 1R 1U 9[f U[f 1U 1

PAGE 101

LQ WKDW SURRI DUH XVHG ,?Wf > Y -$ 1I? -P P nf !.JWfL6}Wf >[@ [V@ Wf[V@ ? 1R 1? Wf AR--AB WWYZr^Wf a ->UV@ >!^ 1U 1 E\ VHFRQG LQHTXDOLW\f -OVO n f 9 -9 1 f > ZfWfL1r 1L: ->[6@ G$Wf VLQFH $[f $[f -UZ)WA f G$Wf ;QaI f G$Wf D ‘ Z r @ D I 0L ->[ $? $nf G$Wf G$^Wf @ 1R 1rQ f OM G$If P As A>U@ ? $@ 1R $fL ORIf L9R G$Wf D0 ZKHUH 0? RR DQG 0 RR VLQFH ZWf DQG ZrWf DUH ERXQGHGf 1R 1[ 1R ->[V@ ? 1L 0 -^[ 1R 1R 1L )^WfG$^Wf 3L DV [ W 6

PAGE 102

7KXV FRQGLWLRQ +fE KROGV 7KH VDPH VHULHV RI LQHTXDOLWLHV JLYHV &RQGLWLRQ ,,, VLQFH ‘D0? 0ff§ > )R[fG$[f SL -6f SL -6f KROGV RQ DFFRXQW RI M)R[f )?[f IRU DOO [ 6 $V IRU WKH UHPDLQLQJ FRQGLWLRQV OHW XV EHJLQ ZLWK FRQGLWLRQ ,9fD %\ VLPLODU DUJXPHQWV WR WKRVH XVHG LQ WKH SURRI RI 7KHRUHP N[f XT[f )[f)L[f S^[f)[f SL[f)L[f ZKHUH W[I[f LV RI WKH VDPH W\SH EXW GRHV QRW QHFHVVDULO\ HTXDO WKH Zr[f IXQFWLRQ HPSOR\HG LQ FDOFXODWLQJ [f 7KDW LV X!]f I[$Lf )[$Lf rf )[f f ZKHUH $L GRHV QRW QHFHVVDULO\ HTXDO $ &RQGLWLRQ ,9rD WKHQ EHFRPHV / 2RRf Z?^[fZr^[f )[f)L[f G$[f 3R[f)R[f SL[f)L[f DQG LV HTXDO WR WKH LQWHJUDO LQ HTXDWLRQ f IRU 9DULrf ZKHQ LXr[f XA[f 7KH ILQLWHQHVV RI WKLV ODVW H[SUHVVLRQ KROGV E\ WKH WZRSRLQW PHFKDQLVP ZKHQ LXr[f DQG X!,[f DUH ERXQGHG RQ r &RQGLWLRQV ,9fE DQG 9r IROORZ E\ DJDLQ HPSOR\LQJ RXU WZRSRLQW PHFKDQLVP LQ FRPELQDWLRQ ZLWK WKH WZR LQHTXDOLWLHV SURRI RI 3URSRVLWLRQ f IURP *LOO f _If,0$cnIf 0f, ->U6? P _$f, /W 1Lf_ 11
PAGE 103

1R 1? \1R 1L D0 1R 1U 9 1R 1 9RLf 9f 1R 1? Q1ZfWf r1 % !f G$Wf O>[6@ 1R L9L UR Qf 1R 1? 1R 1L WWQ Qrrf f O )Wf G?^Wf ZKHUH 0 ERXQGV Z[f DQG Zr[ff 9Ef .Lf 1R 1U D0 O>[6@ D0 > O>[6@ G?^Wf 1R 1U
PAGE 104

N[f )RU LQVWDQFH LI N[f NF[f )[f)L[f S[f)[f SLf)L[ff WKHQ VXEVWLWXWLRQ LQWR f \LHOGV DQ HIILFDF\ H[SUHVVLRQ IRU WKH ORJUDQN VWDWLVWLF *LOO f 7KH DV\PSWRWLF UHODWLYH HIILFLHQF\ RI WZR VWDWLVWLFV FRUUHVSRQGLQJ WR IFL[f DQG N^[f ZLOO EH WKH UDWLR RI WKHLU FRUUHVSRQGLQJ HIILFDFLHV HII[fDff HN[ffHN[ff 0RUH SUHFLVHO\ WKLV IRUPXOD FRPSXWHV WKH HIILFLHQF\ RI D WHVW VWDWLVWLF FRQILJXUHG E\ NL[f ZLWK UHVSHFW WR RQH FRQILJXUHG E\ N[f XQGHU WKH VHTXHQFH RI DOWHUQDWLYHV ^"UY` $ WHVW VWDWLVWLF WKDW UHVXOWV LQ WKH PD[LPXP SRVVLEOH YDOXH IRU f LQ VRPH FODVV IRU WKH JLYHQ WHVWLQJ SUREOHP LV GHVLUDEOH 7KLV PD[LPXP HIILFLHQF\ ZLOO H[LVW IRU D VWDWLVWLF WKDW UHVXOWV LQ WKH ODUJHVW HIILFDF\ YDOXH f *LOO SS f KDV VKRZQ WKDW ZLWKLQ WKH FODVV & FI 6HFWLRQ f D WHVW VWDWLVWLF IRUPHG E\ D PHPEHU .[f WKDW KDV N[f A S[f)>[f SL[f)L[f f DV LWV OLPLWLQJ ZHLJKW IXQFWLRQ ZLOO PD[LPL]H f 7KH DVSHFW RI SURSRUWLRQDOLW\ FRPHV IURP WKH SRWHQWLDO GHSHQGHQFH RI WKH HIILFDF\ RQ WKH FHQVRULQJ GLVWULEXWLRQV *LOO f ,W FDQ EH REVHUYHG WKDW f LV VDWLVILHG E\ D N[f ZLWK D WUXH YDOXH RI $ DQG WKH IXQFWLRQ f WKDW DUH ERWK SUHVHQWHG RQ SDJH RI WKLV PDQXVFULSW

PAGE 105

6R LQ WKH SUHVHQFH RI FHQVRULQJ ZH DUH HQDEOHG WR H[SORUH WKH EHKDYLRU RI Y DJDLQVW FRPSHWLWRUV IURP WKH FODVV I& XQGHU D VHTXHQFH RI ORFDO DOWHUQDWLYHV ^WDW` 3RVVLELOLWLHV IRU WKH FRPSHWLWRUV DUH WHVW VWDWLVWLFV ZLWK GLIIHUHQW YDOXHV IRU $ LQ WKH VFRUH IXQFWLRQV RU WKH ORFDWLRQVKLIW PRGHO WHVW VWDWLVWLFV (IILFLHQF\ ([SUHVVLRQV 7KH YDOXH RI f GHSHQGV RQ D FKRVHQ YDOXH IRU $ $ GHVLUDEOH FKRLFH ZRXOG EH WKH WUXH YDOXH IRU $ GHQRWHG E\ $r RI FRXUVH 'HILQH ZW[f DV WKH ZHLJKW IXQFWLRQ WKDW KDV WKLV WUXH YDOXH DQG LQ WXUQ GHWHUPLQHV [f 6LQFH WKH WUXH YDOXH LV XQNQRZQ LQ SUDFWLFH OHW ZFWO[f EH WKH ZHLJKW IXQFWLRQ EDVHG RQ WKH FKRVHQ YDOXH RI $ $FIRU WKH WHVW VWDWLVWLF Y &RUUHVSRQGLQJO\ OHW X!Wr[f OLP Z$[f 1f§rRR :FK;f r1FK[f EH WKH OLPLWLQJ ZHLJKW IXQFWLRQV RI L[f DQG ZFK[f ,I ZH ZLVK WR FRPSDUH WKH HIILFLHQF\ RI Y EDVHG RQ D FKRVHQ YDOXH IRU $ ZLWK UHVSHFW WR WKH LGHDO FKRLFH RI WKH WUXH YDOXH IRU $ OHW NFK[f EH WKH OLPLWLQJ ZHLJKW IXQFWLRQ FRUUHVSRQGLQJ WR WKH Y WKDW LV XVHG IRU FRQGXFWLQJ WKH WHVW DQG OHW NW[f EH WKH OLPLWLQJ ZHLJKW IXQFWLRQ IRU WKH LGHDO WHVW EDVHG RQ WKH WUXH YDOXH RI $ $OVR VXSSRVH WKDW WKLV LQGH[LQJ LV XVHG RQ WKH FRUUHVSRQGLQJ VFRUH IXQFWLRQV IfXf DQG !Xf DQG DGGLWLRQDOO\ WKH GHQVLW\ [ $f DQG VXUYLYDO IXQFWLRQ )[ $f 1RWH WKH VLPLODULW\ LQ VWUXFWXUH WR WKH XQFHQVRUHG GDWD $5( LQYHVWLJDWLRQV RI 6HFWLRQ ,Q WKH VLWXDWLRQ RI VWXG\LQJ WKH EHKDYLRU RI D WHVW VWDWLVWLF Y LQ WKH SRVVLEOH

PAGE 106

SUHVHQFH RI FHQVRUHG GDWD ZKHQ $ LV PLVVSHFLILHG WKH HIILFDF\ RI WKH OLQHDU UDQN VWDWLVWLF Y LV NHN[fnU[fG$[f 9D Nrf S)[fS)[f ? eE[f)L[f ?:FN?[f )T[f)mf SR)[fSL)L[f f G$[f 3R3LD IFK[$f B )HK[$fO >WM$f B +O0O )R[f)[f MD ? rf )[f [f )[f SRMrf: rfD$: rr UUK[$f B )FK[$f@ )T[f)M[f [f )[f 3R)R[fSL)L [f G$Lf 6LQFH XQGHU WKH QXOO K\SRWKHVLV U )[f )[f/[f )L[f )[f/[[f WKH HIILFDF\ RI Y EDVHG RQ ZFK[f EHFRPHV SRSLD f IFK[$f B )FK[$f I[f )[f IWU$f B )[$f rf )[f )[f /T[f/M[f 3R/D[fS?/?[f G$[f IFK[$f )FK[f$f )[f /[f/?[f rf )[f 3R/[fSL/L[f G$[f f ([SUHVVLRQ f FDQ DOVR WR EH XVHG WR FRPSXWH HIILFLHQFLHV RI WKH VWDQGDUG WHVW VWDWLVWLFV ORJUDQN HWFf EDVHG RQ WKH ORFDWLRQVKLIW PRGHO LQ UHODWLRQ WR WKH PL[HGPRGHO EDVHG WHVW VWDWLVWLFV $V GRQH LQ WKH H[DPSOH RI 6HFWLRQ GHQRWH WKH VFRUH IXQFWLRQV LQ WKH VWDQGDUG WHVWV E\ I!FK^Xf DQG FXf DQG OHW WKH PL[HG PRGHO VFRUH IXQFWLRQV EH JLYHQ E\ I!WXf DQG !WXf 7KH UHVXOWLQJ FDOFXODWLRQ LV WKH 3LWPDQ DV\PSWRWLF UHODWLYH HIILFLHQF\ IRU WKH ORFDWLRQVKLIW EDVHG VWDWLVWLF UHODWLYH WR WKH PL[HGPRGHO VWDWLVWLF ZKHQ WKH XQGHUO\LQJ GLVWULEXWLRQ LV UHSUHVHQWHG E\ WKH PL[WXUH PRGHO DW f

PAGE 107

1H[W OHW XV FRQVLGHU WKUHH VFHQDULRV IRU WKH FHQVRUVKLS GLVWULEXWLRQV FRUUHVSRQGn LQJ WR /[f DQG /?^[f DQG VHH KRZ WKH HIILFDF\ H[SUHVVLRQ f WXUQV RXW 7KHUH LV QR FHQVRULQJ 7KH UHODWLRQ /R[f /?[f KROGV KHUH ZKLFK PHDQV WKDW )[f )?[f )[f 8SRQ WKH VXEVWLWXWLRQ W ORJ)[ff $[f f UHGXFHV WR SR3LDf RR f§RR >$KI)7Hn/$f )UO) Hf$fO I)rHf$f )W)OHff$fO W )}Hmff 9 L )0Hff ))B Hrff -H GW rr UIUK)+Haf$f )UK)0Hff$f I I)+Hfff ))!Hff DQG WKH VHFRQG VXEVWLWXWLRQ f§ X HaO \LHOGV HaOGW 7 3R3?D I >I!FK^Xf a FKXf@ >0Xf a WXf@ GX R f >t}ff fEFKOXf` GX ,W ZRXOG EH FRPIRUWLQJ WR NQRZ WKDW WKH GHQRPLQDWRU RI f UHGXFHV WR D IRUP WKDW LV FRPSDWLEOH ZLWK WKH H[SUHVVLRQ GLVSOD\HG LQ 7KHRUHP f§WKH YDULDQFH RI L IRU XQFHQVRUHG GDWD 7KH QH[W OHPPD KHOSV RXW /(00$ 8QGHU WKH PL[HGPRGHO VHWXS DW f WKH UHODWLRQ L L L RRR KROGV

PAGE 108

3URRI 5HFDOO WKDW L IfXfGX R IURP /HPPD &RPELQHG ZLWK /HPPD WKLV LPSOLHV WKH UHODWLRQ X I!YfGY f§ I!YfGY f§ f§ XfXf X $Q DGGLWLRQDOO\ KHOSIXO UHODWLRQ LV Y n 9 Af§ >Xf .Xf@ f f§ X 1RZ LQWHJUDWLRQE\SDUWV \LHOGV L WXfSFKXf X ‘ !IXf SFKYfGY >WXf !FKXf@ GX R -R R L >WXfO f XfFLXf@c > XfFIFXf@ f§f§WXfGX f§ X > XfFKXf@ f§Af§I!WXfGX L f§ X WfFIFf FIOXfWXfGX FKXfM!WXfGX FK^XfW^XfGX FLWLfI!W^XfGX WXfrmf9 f 9R 7KH VWHS WR WKH ODVW OLQH f LV DLGHG E\ WKH IDFW WKDW f OLP Xf OLP A Of f§ } 9 f RR \ )[f L 5HDUUDQJHPHQW RI WHUPV DW f SURGXFHV WKH UHODWLRQ ’

PAGE 109

/HPPD WHOOV XV WKDW L >!FK^Xf !FOXf@ >I!WXf a WXf@ GX R L L I!FK^XfWfWXfGX WXfOfFKXfGX R R L L FKXf0XfGX FN^XfWXfGX I!FK^Xf0XfGX‘ f R 7KLV LQIRUPV XV WKDW L L >38f Xf@ M!XfGX f R R ZKLFK PDWFKHV WKH LQWHJUDO LQ WKH YDULDQFH H[SUHVVLRQ RI 7KHRUHP %HFDXVH WKH HIILFDF\ E\ f t ff ZKHQ G!FLWf LV L !@^XfGX R WKH FRUUHVSRQGLQJ HIILFLHQF\ IRU PLVVSHFLILHG $ ZKHQ WKHUH LV QR FHQVRULQJ PDWFKHV WKH IRUPXOD GXH WR -RKQVRQ HW DO f VWDWHG LQ 7KHRUHP ,, 7KH FHQVRULQJ GLVWULEXWLRQV DUH HTXDO /HW /[f EH WKH FRPPRQ IXQFWLRQ IRU /[f DQG /?[f 7KHQ ZH KDYH )[f $[f )[f/[f 3XWWLQJ WKHVH LQWR f DORQJ ZLWK WKH WZR LQWHJUDO VXEVWLWXWLRQV LQ WKH ILUVW VFHQDULR OHDGV WR L 3R3?D I >!FKXf F!XfM >I!W^Xf AZf@ /) r XffGX I >0Xf 0Xf@ /)an XffGX f

PAGE 110

7KH UHVXOWLQJ HIILFLHQF\ IRU PLVVSHFLILHG $ LV >W!FN^Xf a FLXf@ >tmf WXf@ 7)B XffGX R I >00 FOXf@ /)an XffGX I >0Xf I!WXf@ /)n XffGX 7KLV LV DQ LPSRUWDQW FDVH VLQFH WKH DVVXPSWLRQ RI HTXDO FHQVRULQJ GLVWULEXWLRQV IRU WKH FRQWURO DQG WUHDWPHQW JURXSV LV RIWHQ GRQH LQ SUDFWLFH f ,,, 7KH FHQVRULQJ GLVWULEXWLRQV DUH QRW HTXDO 7KH VDPH WHFKQLTXHV DV WKRVH XVHG LQ WKH ILUVW WZR VFHQDULRV \LHOGV >W!FK^Xf FLXf@ >0Xf f§ r08f@ >S/r)OLXffS=L)OXff@ A8 3R3?D I>W!FK^Xf !FOXf@ LOWLffRL/L)}OWLffDX 3R /T) IRU WKH HIILFDF\ f DQG >0Xf FLXf@ >0mf a IXf@ R R)OXff)OW-ff 3R/RI)TLXMMSM/A)TLXff GX 9DU)Af9DU)Wrf IRU WKH HIILFLHQF\ RI LQWHUHVW ZLWK L 9DULFr>I!FKXf FOXf@ f f R)OXff7)OXff >SR/)aA Xff 3L/[)anO XffGX f DQG 9DULVff LV GHILQHG LQ WKH VDPH ZD\ 1RWH WKDW WKHVH fYDULDQFHf H[SUHVVLRQV PDWFK XS ZLWK f

PAGE 111

&+$37(5 )2506 2) 7+( 7(67 67$7,67,& ,QWURGXFWLRQ 7KH PHWKRGV GHYHORSHG LQ &KDSWHU 7KUHH ZLOO QRZ EH DSSOLHG WR WR WKH PL[n WXUH PRGHO DVVXPLQJ VRPH RI WKH PRUH FRPPRQ GLVWULEXWLRQDO IRUPV IRU )[ $f 7\SHV RI GLVWULEXWLRQDO IRUPV LQFOXGH WKH QRUPDO ORJLVWLF H[WUHPHYDOXH GRXEOHn H[SRQHQWLDO DQG &DXFK\ 7KH JHQHUDWLRQ RI VSHFLILF VFRUH IXQFWLRQV PDNHV XS 6HFWLRQ 7ZR RI WKLV FKDSWHU 6HFWLRQ 7KUHH IRFXVHV RQ WKH HYDOXDWLRQ RI WKH H[SHFWHG VFRUHV IRU XQFHQVRUHG GDWD &RQGLWLRQV WKDW ZHUH SUHVHQWHG LQ 7KHRUHP DV VXIILFLHQW IRU DQ DV\PSWRWLF QRUPDO GLVWULEXWLRQ RI WKH WHVW VWDWLVWLF EDVHG RQ WKH H[SHFWHG VFRUHV RU WKH DSn SUR[LPDWH VFRUHV DUH DOVR FRQVLGHUHG 6HFWLRQ )RXU FRQVLGHUV VFRUH V\VWHPV IRU WKH FHQVRUHG GDWD FDVH 7KH FRQGLWLRQV LQ 7KHRUHP WKDW DUH VXIILFLHQW IRU WKH XVH RI WKH DSSUR[LPDWH VFRUHV LQ SODFH RI WKH H[SHFWHG VFRUHV LQ WKH FHQVRUHG GDWD WHVW VWDWLVWLF Y DUH LQYHVWLJDWHG

PAGE 112

6FRUH )XQFWLRQV IRU ,QIHUHQFH DERXW U 5HFDOO IURP 7KHRUHP WKDW WKH XQFHQVRUHG DQG FHQVRUHG VFRUH IXQFWLRQV IRU WHVWLQJ +T LW DUH GHILQHG DV IfXf DQG I)a?OXf $f ))an OXf$f Xf UHVSHFWLYHO\ 7KHVH VFRUH IXQFWLRQV ZLOO GHSHQG RQ WKH SDUDPHWHU $ LQ WKH PRGHO f ,Q WKH IROORZLQJ ZH H[KLELW WKH IRUPV RI DQG FRUUHVSRQGLQJ WR VRPH VHOHFWHG ORFDWLRQVKLIW W\SH VXUYLYDO IXQFWLRQ )^[ $f )[$f 7KH LQYHUVH IXQFWLRQ RI WKH VXUYLYDO IXQFWLRQ ) ZKHQ $ LV )aO^O Xf )?OX f :H QRZ FRQVLGHU VRPH VSHFLILF IRUPV IRU ) 1RUPDO VFRUH IXQFWLRQV /HW Rr 7KH XQFHQVRUHG VFRUH IXQFWLRQ LV !PQXf H[S A$ I Xf

PAGE 113

-RKQVRQ HW DO f FRQVLGHUHG WKH UHVXOWLQJ DSSUR[LPDWH QRUPDO VFRUHV ZKLFK DULVH IURP WKH VXEVWLWXWLRQ X 1 DW WKH REVHUYHG SRLQW [SM 6LQFH )[ f§ $f GRHV QRW KDYH D FORVHG IRUP WKH FHQVRUHG VFRUH IXQFWLRQ FDQ RQO\ EH UHSUHVHQWHG DV ,!Xf LV DERYH A ))aO Xf $f APQXf f§ X /RJLVWLF VFRUH IXQFWLRQV +HUH ZH KDYH )[ $f Hr$f Ha[$f f ZKHUHXSRQ WKH XQFHQVRUHG VFRUH IXQFWLRQ LV JLYHQ E\ O H)f2}f APOZf H I HO)BLff$@ 8VH RI WKH HTXDWLRQ H[S ) r f§ Xff f§ X X SURYLGHV WKH VLPSOLILFDWLRQ H$ H$ XO f§ H$f 6LPLODUO\ WKH FHQVRUHG VFRUH IXQFWLRQ WXUQV RXW WR EH POXf H/ H$ XO f§ H$f

PAGE 114

'RXEOH([SRQHQWLDO VFRUH IXQFWLRQV )RU WKLV GLVWULEXWLRQ )[ $f ,HU$ff LI D OB,H[$ff LI [ 7KHUHIRUH WKH UHTXLUHG XQFHQVRUHG VFRUH IXQFWLRQ LV f Ha$ f§ LI )?O Xf PGHXf H)fff$ LI )BO Xf $ H$O :LWK WKH XVH RI WKH LQYHUVH IXQFWLRQ ORJ>X@ LI )O Xf $ )OXf WKLV FDQ EH UHH[SUHVVHG DV APGHXf m LI )BO Xf ORJ>OXf@ LI )BO Xf $ f§ LI X 7)S a LI ? X ?H $ H OXf V$ f§ LI $ X 7KH FHQVRUHG VFRUH IXQFWLRQ LV H[SUHVVHG DV n XOHa$f X APGHZf LI X f§ LI X L3B$ X f§Xf f A 8 f§ H f LI f§ ?H $ X &DXFK\ VFRUH IXQFWLRQV :H KDYH )[ $f DUFWDQ[ f§ $f 7 VR WKDW WKH XQFHQVRUHG VFRUH IXQFWLRQ LV !PFXf $)a Xf $f )O Xf $ff

PAGE 115

7KH LQYHUVH IXQFWLRQ LV )BO Xf WDQ UX Aff VR WKDW WKH XQFHQVRUHG VFRUH IXQFWLRQ DOVR HTXDOV WDQ UX f§ Lf_ W!0F^Xf f§c I WDQ UX f§ _ff§ $M 7KH FHQVRUHG VFRUH IXQFWLRQ LV OODUFWDQ)O8f$ff f§ X ([WUHPH9DOXH VFRUH IXQFWLRQV 8QOLNH WKH RWKHU GHQVLW\ IRUPV ZH H[DPLQHG WKXV IDU WKH H[WUHPHYDOXH IRUP LV QRW D V\PPHWULF GHQVLW\ IXQFWLRQ 7KHUH DUH WZR W\SHV RI H[WUHPHYDOXH GHQVLWLHV ZH FRQVLGHU KHUH 2QH W\SH LV I[ $f H[S[ f§ $ f§ f 7KH RWKHU GHQVLW\ IRUP LV I^[ $f H[S f§[ f§ $f f§ f 1RWH WKDW WKHVH DUH MXVW WKH GLVWULEXWLRQV RI UDQGRP YDULDEOHV ; f§ $ DQG f§ ; f§ $f ZKHUH ; KDV WKH GHQVLW\ I[ f JLYHQ E\ f 7KH GHQVLW\ I[ f DW f FRUUHVSRQGV WR WKH UDQGRP YDULDEOH ; ORJ < ZKHUH < KDV WKH H[SRQHQWLDO GHQVLW\ IRUP )RU WKH GHQVLW\ IRUP f WKH LQYHUVH IXQFWLRQ LV ) ; W[f ORJf§ ORJO Xff

PAGE 116

ZKLFK OHDGV WR WKH XQFHQVRUHG VFRUH IXQFWLRQ A0(YZf H $ f§ 8< a DQG WKH FHQVRUHG VFRUH IXQFWLRQ A0(Ymf OXfH$nO 7KHUH DUH VRPH SUREOHPV ZLWK WKH DV\PSWRWLF SURSHUWLHV RI WKH WHVW VWDWLVWLF JHQn HUDWHG E\ WKH VFRUH IXQFWLRQ FRUUHVSRQGLQJ WR WKH GHQVLW\ f 6SHFLILFDOO\ WKH LQWHJUDO FRPSRQHQW RI WKH DV\PSWRWLF YDULDQFH LQ 7KHRUHP RI WKH VFRUH IXQFn WLRQ LV LQILQLWH IRU YDOXHV RI $ ORJ WKHUHE\ YLRODWLQJ WKH FRQGLWLRQ LLf RI 7KHRUHP $OVR WKH H[LVWHQFH RI WKH FHQVRUHG VFRUH IXQFWLRQ LV XQFOHDU EHFDXVH FRQGLWLRQ LLLf RI 7KHRUHP ZKLFK SHUPLWV H[FKDQJH RI GLIIHUHQWLDWLRQ DQG LQWHJUDWLRQ IDLOV IRU $ ORJ )RU WKH PL[WXUH PRGHO f WKH DV\PSWRWLF SURSHUWLHV RI WKH WHVW VWDWLVWLF L EDVHG RQ VXFK VFRUH IXQFWLRQV FDQQRW EH HVWDEOLVKHG E\ WKH PHWKRGV LQ WKLV PDQXVFULSW 1RZ VXSSRVH WKH GHQVLW\ IRU WKH UHVSRQGHUV LV DV JLYHQ DW f I[ $f H[S f§L f§ $f f§ HBAa$rf 7KH XQFHQVRUHG VFRUH IXQFWLRQ LV !PHY^Xf H[S $ Ha) XfH$ ff ZKLFK FDQ EH VRPHZKDW VLPSOLILHG E\ VXEVWLWXWLRQ RI WKH IRUPXOD ) ; Xf ORJORJXff

PAGE 117

WR JHW !0(YOf H$XfH f§ 7KH FHQVRUHG VFRUH IXQFWLRQ LV IRXQG WR EH PHYXf H$ Hr f§ 8 8 f§ 8 f§ 8 f§ 8 &RQRYHU DQG 6DOVEXUJ f FDPH XS ZLWK WKH VDPH IRUP DV I!PHYmf IRU I!Xf IURP f XVLQJ D /HKPDQQ DOWHUQDWLYH IRU WKH QRQUHVSRQGHUV VHH RXU 6HFWLRQ f WKHLU SDUDPHWHU D FRUUHVSRQGV WR RXU H$ 3DUDOOHO WR WKH VFRUH IXQFWLRQV IURP PHYXf DQG APHYXf IUrP f SUREOHPV RFFXU IRU YDOXHV RI $ f§ ORJ ORJ IRU WKH VFRUH IXQFWLRQV APHYXf DQG PHYPf 1RZ FRQVLGHU )[ $f WR EH RI WKH /HKPDQQW\SH 8QGHU WKH /HKPDQQ DOWHUQDWLYH PRGHO LLLf LQ 6HFWLRQ WKH JHQHUDWHG VFRUH IXQFWLRQV DUH HTXLYDOHQW WR WKRVH LQ WKH H[WUHPHYDOXH FDVH UHSUHVHQWHG E\ !PHYXf DQA APHYXf IURP f 5HFDOO WKDW WKHVH ODVW VFRUH IXQFWLRQV ZHUH UHMHFWHG GXH WR ODUJHVDPSOH EHKDYLRU FRQVLGHUDWLRQV &RQRYHU DQG 6DOVEXUJ f UHFRPPHQGHG WKDW VXFK VFRUH IXQFn WLRQV GHULYHG IURP WKHLU 0RGHO f QRW EH XVHG EHFDXVH fLW DSSHDUV WR KDYH ORZ SRZHU LQ WKH H[DPSOHV ZH LQYHVWLJDWHGf 3UHVXPDEO\ WKH DXWKRUV UHIHU WR WKH HPn SLULFDO SRZHU LQ WKH 0RQWH &DUOR VWXG\ WKH\ UDQ DQGRU WKH UHVXOWV IURP WKH UHDO GDWD VHWV ZKHUH OLQHDU UDQN WHVWV ZHUH DSSOLHG LQ WKHLU SDSHU 8QIRUWXQDWHO\ WKH SDSHU GRHV QRW JLYH WKH ILJXUHV IURP WKH 0RQWH &DUOR VWXG\ 7KHUH ZDV QR PHQWLRQ RI DQ LQILQLWH YDULDQFH SUREOHP IRU FHUWDLQ YDOXHV RI D HLWKHU 7KH /HKPDQQDOWHUQDWLYH PRGHO FRUUHVSRQGLQJ WR LYf LQ 6HFWLRQ \LHOGV WKH VDPH VFRUH IXQFWLRQV "!PHYXf DQG APHYZf GHULYHG IURP WKH H[WUHPHYDOXH IRUP

PAGE 118

f 7KHVH FRUUHVSRQG WR &RQRYHU DQG 6DOVEXUJfV f VFRUH IXQFWLRQV DULVLQJ IURP WKHLU 0RGHO 7KHUHIRUH LQ VXEVHTXHQW LQYHVWLJDWLRQV WKH /HKPDQQ PRGHO LYf ZLOO LPSOLFLWO\ EH FRQVLGHUHG XQGHU WKH H[WUHPHYDOXH ODEHO WKDW FRUUHVSRQGV WR WKH VFRUH IXQFn WLRQV 3PHYXf DQG !PHYXf GHULYHG IURP WKH GHQVLW\ IRUP f 7KH /HKPDQQ DOWHUQDWLYH PRGHO LLLf LQ 6HFWLRQ DQG WKH VFRUH IXQFWLRQV !PHYXf DQA APHYXf IURP f ZLOO QRW EH FRQVLGHUHG DW DOO VLQFH VXEVHTXHQW LQYHVWLJDWLRQV LQ WKLV PDQXVFULSW VXFK DV HIILFLHQFLHV DQG VLPXODWLRQV DVVXPH WKDW $ 8QFHQVRUHG 'DWD ([SHFWHG 6FRUHV ,Q WKH OLWHUDWXUH UHYLHZ RI 6HFWLRQ WKH QRUPDO GLVWULEXWLRQ XQFHQVRUHG VFRUH IXQFWLRQ tPQXf DV UHSRUWHG E\ -RKQVRQ HW DO f ZDV FRQVLGHUHG 5HFDOO WKDW H[SHFWHG VFRUHV FDQ EH HYDOXDWHG E\ WDNLQJ WKH H[SHFWDWLRQ RI M!8f ZKHUH 8 LV DVVXPHG WR KDYH WKH EHWD GHQVLW\ ZLWK SDUDPHWHUV L DQG 1 f§ L 6LQFH !PQAf GRHV QRW KDYH D FORVHG IRUP WKH H[SHFWHG VFRUH F PXVW EH QXPHULFDOO\ HYDOXDWHG ,Q WKH IROORZLQJ H[SHFWHG VFRUHV IRU RWKHU GLVWULEXWLRQV DUH UHSRUWHG 7KHRUHP VWDWHV VXIILFLHQW FRQGLWLRQV IRU OLQHDU UDQN WHVWV EDVHG RQ I!Xf WR KDYH DV\PSWRWLF QRUPDOLW\ SURSHUWLHV &RQGLWLRQ Lf VWDWHG WKDW MfXf PXVW EH PRQRWRQLF ZKLOH &RQGLWLRQ LLf RI 7KHRUHP VWLSXODWHG WKDW L W!^XfGX RR R 7KH H[LVWHQFH RI WKHVH WZR FRQGLWLRQV DUH DOVR GLVFXVVHG LQ WKH UHPDLQGHU RI WKLV VHFWLRQ

PAGE 119

/RJLVWLF H[SHFWHG VFRUHV 2EWDLQLQJ DQ DQDO\WLF H[SUHVVLRQ IRU WKH H[SHFWHG VFRUHV UHTXLUHV VRPH DOJHEUD IRU WKH ORJLVWLF GLVWULEXWLRQ 7KH XQFHQVRUHG H[SHFWHG VFRUH F VDWLVILHV L Of-9LffO Q? L r mnL H$ XO f§ H$f GXL GX^ 7 GX L \YU $7Ln f e M f U LL  1f§Mf§ -8n B f§ /LAf 7KH EUDFNHWHG H[SUHVVLRQ LQ WKH ODVW OLQH RI WKH HTXDWLRQ FDQ EH UHSUHVHQWHG DV D TXDQWLW\ LQYROYLQJ D K\SHUJHRPHWULF IXQFWLRQ *UDGVKWH\Q DQG 5\]KLN f SURYLGH D FRPSOHWH GHWDLOHG UHIHUHQFH WR WKH SURSHUWLHV RI K\SHUJHRPHWULF IXQFWLRQV 8VLQJ WKH LQWHJUDO UHSUHVHQWDWLRQ JLYHQ RQ SDJH RI *UDGVKHW\Q DQG 5K\]LN f r OfO1 rf F 1? 1 V ff§f%1 M f) 1M1M OM Hf ZKHUH %D-f UTfU"f U D S\ U VWDQGV IRU WKH *DPPD IXQFWLRQ DQG )^D W ]f D f DT Of f TT OfT f f" f f f f f f f

PAGE 120

6WUDLJKWIRUZDUG VXEVWLWXWLRQ LQWR WKH DERYH H[SUHVVLRQ VKRZV WKDW ) 1U1M Hf  f Ha$f? VR WKDW F H 1? H$ ,1 Ln ; < f):$LM OOHDfO M ? M $7 IH LYf A } f M -9 m Mf -9 Mf ( 77A7977A f m< !a LV WKH H[SHFWHG VFRUH FRUUHVSRQGLQJ WR ;M L 79 IRU D ORJLVWLF GLVWULEXWLRQ )RU WKH FRQGLWLRQV RI 7KHRUHP ZH KDYH tOff m$fA f >H$ XO H$f@ ZKLFK LV SRVLWLYH YDOXHG IRU DOO X e f VR WKH PRQRWRQLFLW\ FRQGLWLRQ Lf KROGV L 7KH H[SUHVVLRQ IRU A/XfGX LV R H$ a Of H$ ZKHQ $ DQG LV ILQLWH +HQFH FRQGLWLRQ LLf RI 7KHRUHP LV VDWLVILHG 'RXEOH([SRQHQWLDO H[SHFWHG VFRUHV (YDOXDWLRQ RYHU WKH WKUHH UHJLRQV RI WKH VFRUH IXQFWLRQ JLYHV f§ LI 8L Fm a A LI i O_H$ OH$ LI f§ ?W $ 8L

PAGE 121

&KHFNLQJ WKH PRQRWRQLFLW\ FRQGLWLRQ Lf LQ 7KHRUHP \LHOGV LI X AXf LI X OH$f LI OH$f X 7KXV FRQGLWLRQ Lf LV YHULILHG )RU WKLV GLVWULEXWLRQ PGHXf aa PGHXfX $ a ZKHQ $ +HQFH FRQGLWLRQ LLf RI 7KHRUHP LV DOVR YHULILHG &DXFK\ H[SHFWHG VFRUHV 7KH H[SHFWHG VFRUH UHTXLUHV QXPHULFDO HYDOXDWLRQ 7KH LQWHJUDWLRQ H[SUHVVLRQ ZULWWHQ LQ WKH QRUPDO FDVH DERYH FDQ EH HPSOR\HG 7KH XQFHQVRUHG VFRUH IXQFWLRQ APFXf LV QRW VWULFWO\ PRQRWRQLF VR 7KHRUHP FDQQRW EH DSSOLHG 6LQFH WKH FRQGLWLRQ Lf LV VWDWHG DV D VXIILFLHQW FRQGLWLRQ SHUKDSV DQ DOWHUQDWLYH FRQGLWLRQ DOORZV WKH VDPH UHVXOWV IRU WKH &DXFK\ GLVWULEXWLRQ ,QGHHG WKH WKHRU\ GHYHORSHG LQ &KDSWHU 7KUHH IRU SRWHQWLDOO\ FHQVRUHG GDWD FDQ EH DSSOLHG FI 6HFWLRQ f WR DFKLHYH WKH UHVXOWV RI 7KHRUHP IRU WKH &DXFK\ GLVWULEXWLRQ :H KDYH IRU $ APFXf
PAGE 122

([WUHPH9DOXH H[SHFWHG VFRUHV 1RWH WKDW WKH /HKPDQQDOWHUQDWLYH PRGHO LYf LQ 6HFWLRQ LV LPSOLFLWO\ FRQVLGn HUHG KHUH E\ RXU GLVFXVVLRQ RI H[WUHPHYDOXH VFRUH IXQFWLRQV LQ 6HFWLRQ 6WUDLJKWn IRUZDUG LQWHJUDWLRQ \LHOGV 1? 7H$ LOf &r a L f 71 H$f B/ ,I H$ LV LQWHJHUYDOXHG ZH JHW WKH IXUWKHU VLPSOLILFDWLRQ 11OfLf L9 H$ f§ f f f f H$  f§ f f ZKLFK PDWFKHV WKH UHVXOW REWDLQHG E\ &RQRYHU t 6DOVEXUJ f XQGHU WKHLU /HKPDQQW\SH PL[HG 0RGHO 7KH ILUVW GHULYDWLYH RI LAPHYAf LV APHYXf f§ H$H$ f§ OfXH ZKLFK WDNHV RQ VWULFWO\ SRVLWLYH YDOXHV RYHU f 7KXV FRQGLWLRQ Lf RI 7KHRUHP LV VDWLVILHG 7KH H[SUHVVLRQ IRU APHYX0 ZKHQ $ LV G$ H$ VR WKDW FRQGLWLRQ LLf RI 7KHRUHP DOVR KROGV &HQVRUHG 'DWD ([SHFWHG 6FRUHV :H QRZ FRQVLGHU HYDOXDWLRQ RI H[SHFWHG VFRUHV ZKHQ FHQVRUHG GDWD LV SUHVHQW XQGHU WKH PRGHO f DQG WKH UDQGRP FHQVRUVKLS PRGHO RI 6HFWLRQ 7KH

PAGE 123

,OO GHULYHG GHQVLW\ IRUP JrXf DW f LQ WKH SUHYLRXV FKDSWU LV HPSOR\HG IRU ERWK WKH XQFHQVRUHG DQG FHQVRUHG H[SHFWHG VFRUHV 5HFDOO WKDW LQ 7KHRUHP WKHUH ZHUH WKUHH FRQGLWLRQV JLYHQ WKDW DUH VXIILFLHQW IRU WKH DSSUR[LPDWH XQFHQVRUHG DQG FHQVRUHG VFRUHV WR FRQYHUJH LQ SUREDELOLW\ DV 1 f§r RR WR WKH H[SHFWHG VFRUHV F DQG & UHVSHFWLYHO\ ,W ZDV SRLQWHG RXW LQ WKH GLVFXVVLRQ DIWHU SUHVHQWDWLRQ RI 7KHRUHP WKDW FRQGLWLRQ & IROORZV IURP WKH YDULDQFH H[SUHVVLRQ f REWDLQHG LQ 7KHRUHP &RQGLWLRQ &O UHIHUV WR WKH H[LVWHQFH DQG FRQWLQXLW\ RI WKH ILUVW DQG VHFRQG GHULYDWLYHV RI WKH XQFHQVRUHG VFRUH IXQFWLRQ I!Xf RYHU f 3DUW RI &O KDV DOUHDG\ EHHQ LQGLUHFWO\ DGGUHVVHG LQ 6HFWLRQ ZKHQ WKH PRQRWRQLFLW\ FRQGLWLRQ Lf RI 7KHRUHP ZDV GLVFXVVHG ,Q RUGHU WR LQYHVWLJDWH WKH H[LVWHQFH RI WKH FRQGLWLRQV &O DQG & WKH GHULYDWLYHV M!nXf DQG DUH H[DPLQHG IRU HDFK RI RXU FKRVHQ GLVWULEXWLRQDO IRUPV RI )[f§$f $QRWKHU NH\ SRLQW WKDW LV LQYHVWLJDWHG EHORZ LV WKH ERXQGHGQHVV RI WKH ZHLJKW IXQFWLRQ Z[f DW f 6XSSRVH $? DQG $ DUH SRVLWLYH FRQVWDQWV 7KH VXIILFLHQW FRQGLWLRQV JLYHQ LQ /HPPD DUH HTXLYDOHQW WR WKH XQFHQVRUHG VFRUH IXQFWLRQ -!Xf VDWLVI\LQJ OLP ^Xf $?? OLPG!Xf $ SURYLGLQJ XV ZLWK DQRWKHU PHDQV WR FKHFN WKHVH FRQGLWLRQV /HPPD DQG WKH FRQWLQXLW\ RI )[ f§ $f ZHUH VXIILFLHQW IRU Z[f WR EH ERXQGHG

PAGE 124

1RUPDO H[SHFWHG VFRUHV %\ QDWXUH RI WKH VFRUH IXQFWLRQV "!Xf DQG mf WDNLQJ WKHLU H[SHFWDWLRQ WR ILQG F DQG & UHVSHFWLYHO\ UHTXLUHV QXPHULFDO LQWHJUDWLRQ ZLWK UHVSHFW WR WKH GHQVLW\ f &RQGLWLRQ & RI 7KHRUHP ZLOO QRW EH VDWLVILHG DV ERWK WKH ILUVW DQG VHFRQG GHULYDWLYHV RI I!Xf DUH XQERXQGHG DV X f§! 2I FRXUVH WKH DSSUR[LPDWH VFRUHV DUH D PXFK PRUH SUDFWLFDO FKRLFH DQ\KRZ IRU WKH WHVW VWDWLVWLF IURP D FRPSXWDWLRQDO VWDQGSRLQW 7KH OLPLW RI WKH ZHLJKW IXQFWLRQ Z[f DW f DV [ f§ f§RR LV EXW WKH OLPLW DV [ f§ RR LV DQRWKHU PDWWHU %RWK VFRUH IXQFWLRQV DUH XQERXQGHG DV [ JURZV ODUJH RU HTXLYDOHQWO\ DV X f§ /f+RSLWDOfV UXOH FDQQRW EH DSSOLHG DV DOO GHULYDWLYHV RI I[ $f DQG [f JURZ LQILQLWHO\ ODUJH LQ WKH OLPLW DV ZHOO +HQFH WKH QRUPDO GLVWULEXWLRQ LV QRW GLUHFWO\ FRYHUHG E\ 7KHRUHP *LOO f HQFRXQWHUHG D VLPLODU VLWXDWLRQ IRU WKH ORFDWLRQVKLIW PRGHO ZKHQ WKH XQGHUn O\LQJ GLVWULEXWLRQ LV QRUPDO 5HIHU WR KLV ([DPSOH S f ,Q WKDW FDVH WKH FRUUHVSRQGLQJ ZHLJKW IXQFWLRQ WR Zr[f IRU WKH ORFDWLRQVKLIW PRGHO ZDV en^[f nrf rf rf )[< 7KH WURXEOHVRPH SRLQW LV [ f§ f§RR +RZHYHU KLV SDJH f SURSRVDOV GHDO ZLWK WKLV LQ RUGHU WR VXFFHVVIXOO\ GHULYH WKH DV\PSWRWLF QRUPDOLW\ SURSHUWLHV WKDW ZRXOG EH H[SHFWHG XQGHU WKH QXOO K\SRWKHVLV 7KH SURSRVDOV FDQ EH DGDSWHG IRU RXU WK[f IRU WKH PL[HG PRGHO DW f 7KH UHDGHU LV UHIHUUHG WR *LOO S f§f IRU GHWDLOV

PAGE 125

/RJLVWLF H[SHFWHG VFRUHV 8VLQJ WKH GHQVLW\ rXWf DW f DQ XQFHQVRUHG H[SHFWHG VFRUH ZLOO LQYROYH WKH LQWHJUDWLRQ $LXfr -R \ [ $OXfA -R H$ f§ H$fXL GX^ 8 WXn GX^ >f§ M %LOnW\)IU85M OLOHrf f ^L Hf Lm$fM f f f 5M Of5M f f f E\ WKH VDPH WHFKQLTXHV VXUURXQGLQJ WKH K\SHUJHRPHWULF IXQFWLRQ H[SRXQGHG XSRQ LQ WKH ORJLVWLF H[DPSOH RI 6HFWLRQ 7KXV WKH H[SHFWHG VFRUH LV F H m ]Lf Qr Y\ L M L Q LK5Mf LQr 9 9f ^e nf$  QAAf 5@ A r

PAGE 126

L Q r YU L ( M L Q ^5L5MfA r 5M Kf I IHSfIO? fL H< L 6LPLODUO\ WKH FHQVRUHG H[SHFWHG VFRUH WXUQV RXW WR EH &L Qrr ( \ L f M L I_ IO B Af 8 R AL rf L 7KH VFRUH IXQFWLRQ APOXf LV GHILQHG DQG FRQWLQXRXV RYHU >@ 7KXV LQ[f LV ERXQGHG IRU DOO [ DQG IXUWKHUPRUH f§ H$f S?Xf rmf >H$ H$fX@ H$f >H$ H$fX@ VR WKDW FRQGLWLRQV &O DQG & RI 7KHRUHP DUH VDWLVILHG 'RXEOH([SRQHQWLDO H[SHFWHG VFRUHV 7KH EHWD IXQFWLRQ LV LQYROYHG ZLWK WKH H[SHFWDWLRQV ,I 8^ WKHQ F H $ f§ DQG F ,, ,I X f§ OfH$ WKHQ L L X5LUf 0O & $ 9f 85 ( ‘%O5M f§ f 'n <+5L5Mf

PAGE 127

DQG F IQAff§f§ ? L L L QLLLILLf ,,, ,I f§ OfH$ X WKHQ F & H$ f§ 7KH VWUXFWXUH IRU WKH UHJLRQV DQG ,,, DERYH DORQJ ZLWK WKH PRQRWRQLFLW\ RI IfXf LPPHGLDWHO\ LQVXUHV WKDW Z[f LV ERXQGHG DQG WKDW FRQGLWLRQV &O DQG & RI 7KHRUHP REWDLQ 5M f§ f f§ $n f &DXFK\ H[SHFWHG VFRUHV $V ZLWK WKH QRUPDO GLVWULEXWLRQ WKH QDWXUH RI WKH VFRUH IXQFWLRQV !PFXf DQG PFmf VXJJHVWV QXPHULFDO LQWHJUDWLRQ IRU WKH H[SHFWDWLRQ RYHU f $ GRXEOH DSSOLFDWLRQ RI /f+RSLWDOfV UXOH IRU HYDOXDWLQJ HDFK OLPLW JLYHV I[ $f r $f UBBRR I[f [arr I[f VR WKDW Z[f DW WKH SRLQWV f§RR DQG RR 7KHQ DSSOLFDWLRQ RI /HPPD LV DSSURSULDWH DV Z[f LV ERXQGHG IRU DOO [ 7KH ILUVW DQG VHFRQG GHULYDWLYHV RI I!Xf DUH PHVV\ H[SUHVVLRQV EXW LQGLFDWH WKDW FRQGLWLRQV &O DQG & RI 7KHRUHP DUH VDWLVILHG 7KH &DXFK\ GLVWULEXWLRQ LV DQ H[DPSOH ZKHUH 7KHRUHP LV PRUH JHQHUDOO\ DSSOLFDEOH WKDQ 7KHRUHP ZKHQ WKHUH LV QR SUHVHQFH RI FHQVRULQJ LQ WKH GDWD 6SHFLILFDOO\ WKH PRQRWRQLFLW\ FRQGLWLRQ Lf LQ 7KHRUHP RI WKH VFRUH IXQFWLRQ M!0FXf LV UHOD[HG

PAGE 128

([WUHPH9DOXH H[SHFWHG VFRUHV 7KH LQWHJUDWLRQ SURGXFHV D EHWD IXQFWLRQ DJDLQ 7KLV JLYHV WKH H[SUHVVLRQV &L 9Mn L H$AfO n Q 5L U!f OO DQG &L IULA(f§ E Yn L Q Q 1Mf L L H$1Mf/ &OHDUO\ "!PHYZf LV ERXQGHG RQ >@ DQG VLQFH WKH ILUVW DQG VHFRQG GHULYDWLYHV DUH SURSRUWLRQDO WR WKH VFRUH IXQFWLRQ FRQGLWLRQV &O DQG & KROG $GGLWLRQDOO\ Z[f LV ERXQGHG RQ WKH H[WHQGHG UHDO OLQH VLQFH I^[$f Q IL[$f D KUQ ‘ KUQ Y W f H$ IL[f IL[f

PAGE 129

&+$37(5 &203$5$7,9( 678',(6 7KH UHVXOWV RI WKH ODVW WZR FKDSWHUV HQDEOH XV WR HYDOXDWH WKH SHUIRUPDQFH RI OLQn HDU UDQN WHVW VWDWLVWLFV GHULYHG IURP WKH PL[WXUH PRGHO DW f 6LQFH WKH VFRUHV RI WKHVH OLQHDU UDQN VWDWLVWLFV GHSHQG RQ WKH SDUDPHWHU $ 3LWPDQ DV\PSWRWLF UHOn DWLYH HIILFLHQFLHV FDQ EH XVHG WR KHOS FKRVH D YDOXH RI $ WR FRQGXFW WKH WHVW ,Q WKH OLWHUDWXUH UHYLHZ RI 6HFWLRQ DQ H[DPSOH RI WKH 3LWPDQ DV\PSWRWLF UHODWLYH HIILn FLHQF\ IRU PLVVSHFLILHG $ LQ WKH FDVH RI D PL[HG QRUPDO GLVWULEXWLRQ ZDV UHSRUWHG ,QFOXGHG LQ WKDW H[DPSOH ZDV DQRWKHU HIILFLHQF\ FRPSDULVRQ RI QRUPDO VFRUHV IURP WKH VWDQGDUG ORFDWLRQVKLIW PRGHO UHODWLYH WR PL[HGPRGHO VFRUHV ZKHQ WKH XQGHUO\n LQJ GLVWULEXWLRQ LV PL[HG QRUPDO 1RZ ZH FDQ H[WHQG WKHVH W\SHV RI FRPSDULVRQV WR RWKHU GLVWULEXWLRQV DQG DOORZ IRU FHQVRULQJ 7KH UHVXOWLQJ HIILFLHQFLHV DUH UHSRUWHG LQ 6HFWLRQ )LQLWH VDPSOH FRPSDULVRQV LQYROYLQJ PLVVSHFLILHG $ LQ WKH PL[HGPRGHO VFRUHV DQG FRPSDULVRQV RI PL[HGPRGHO VFRUHV YV ORFDWLRQVKLIW PRGHO VFRUHV DULVH IURP VLPXODWLRQV WKDW ZHUH FRQGXFWHG DQG DUH GLVFXVVHG LQ 6HFWLRQ $ YDULHW\ RI FHQn VRULQJ PHFKDQLVPV DQG XQGHUO\LQJ GLVWULEXWLRQDO IRUPV DUH FRQVLGHUHG WR HYDOXDWH WKH SHUIRUPDQFH RI WKH PL[HGPRGHO WHVWV DQG WKH ORFDWLRQVKLIW PRGHO WHVWV 6RPH UHFRPPHQGDWLRQV RQ VFRUHV WR XVH LQ SUDFWLFH DUH SUHVHQWHG KHUH %DVHG RQ WKHVH

PAGE 130

UHFRPPHQGDWLRQV SHUIRUPDQFH RI VHOHFWHG WHVWV RQ DQ XQFHQVRUHG GDWD H[DPSOH DQG D FHQVRUHG GDWD H[DPSOH LV LOOXVWUDWHG LQ 6HFWLRQ 3LWPDQ $V\PSWRWLF 5HODWLYH (IILFLHQFLHV ,W LV DJDLQ QRWHG WKDW $5( LV DQ DEEUHYLDWLRQ IRU 3LWPDQ DV\PSWRWLF UHODWLYH HIILFLHQF\ LQ WKLV PDQXVFULSW 7KH XVDJH RI WKH ORQH ZRUG fHIILFLHQF\f LPSOLFLWO\ UHIHUV WR 3LWPDQ DV\PSWRWLF UHODWLYH HIILFLHQF\ 5HFDOO WKDW IRU XQFHQVRUHG GDWD 7KHRUHP JLYHV D IRUPXOD WR EH XVHG WR HYDOXDWH $5( IRU VRPH SDUWLFXODU GLVWULEXWLRQV ZKHQ WKH XQNQRZQ SDUDPHWHU LV PLVVSHFLILHG 7KLV ZDV UHLWHUDWHG LQ VFHQDULR f RI HIILFLHQF\ H[SUHVVLRQV LQ 6HFWLRQ ,Q DQ H[DPSOH LQ 6HFWLRQ ZH DOVR GLVFXVVHG WKH XVH RI $5( WR FRPSDUH WKH SHUIRUPDQFH RI WKH PL[HGPRGHO VFRUHV WHVW ZLWK WKH VWDQGDUG ORFDWLRQ VKLIW VFRUHV WHVW $W WKDW SRLQW WKH QRUPDO GLVWULEXWLRQ ZDV XVHG DV DQ LOOXVWUDWLRQ %HFDXVH WKH HIILFLHQF\ H[SUHVVLRQV GHULYHG LQ 6HFWLRQ XQGHU WKH UDQGRP FHQn VRUVKLS PRGHO DUH JHQHUDOL]DWLRQV RI WKH XQFHQVRUHG GDWD HIILFLHQF\ H[SUHVVLRQ LQ 7KHRUHP WKH $5( HYDOXDWLRQV IRU RWKHU GLVWULEXWLRQDO IRUPV WKDW FRQVLGHU ERWK 1R FHQVRULQJ DQG 9DULRXV FHQVRULQJ SDWWHUQV ZLOO EH UHSRUWHG WRJHWKHU 7R VXPPDUL]H WZR W\SHV RI $5( DUH HYDOXDWHG

PAGE 131

0LVVSHFLILHG $ DQG 0LVVSHFLILHG PRGHO 'HVFULSWLRQ RI FHQVRULQJ SDWWHUQV )RU DOO $5( HYDOXDWLRQV WKH FHQVRULQJ GLVWULEXWLRQV ZHUH DVVXPHG WR EH HTXDO IRU ERWK WKH FRQWURO JURXS DQG WKH WUHDWPHQW JURXS $ IRUPXOD IRU HIILFLHQF\ LV JLYHQ DW f 8QGHU UDQGRP FHQVRUVKLS WKH WZR VHOHFWHG FHQVRULQJ GLVWULEXWLRQV IRU WKH VXUYLYDO WLPHV ZHUH 7KH GLVWULEXWLRQ RI WKH QDWXUDO ORJDULWKP RI DQ H[SRQHQWLDO UDQGRP YDULDEOH ZLWK KD]DUG UDWH $ L H WKH H[WUHPHYDOXH GLVWULEXWLRQ /^[f H[S[ ORJO$f HrLrVL$fff f§RR [ RR $ 7KH GLVWULEXWLRQ RI WKH QDWXUDO ORJDULWKP RI D XQLIRUP UDQGRP YDULDEOH ZLWK VXSSRUW $f L H /[f f§f§HU f§RR [ ORJ $ 0 0 9DOXHV RI WKH SDUDPHWHUV $ DQG 0 FDQ EH VHOHFWHG WR JLYH GHVLUHG FHQVRULQJ UDWHV IRU WKH FRQWURO DQG WUHDWPHQW JURXSV XQGHU WKH QXOO K\SRWKHVLV +T U )RU RXU $5( HYDOXDWLRQV EHORZ FHQVRULQJ UDWHV RI b b DQG b ZHUH VHOHFWHG ,QFOXGLQJ WKH XQFHQVRUHG FDVH LH D b FHQVRULQJ UDWH $5( HYDOXDWLRQV IRU VHYHQ GLIIHUHQW FHQVRULQJ SDWWHUQV IRU D JLYHQ VXUYLYDO GLVWULEXWLRQ ZHUH FRPSXWHG IRU WKH PLVVSHFLILHG $ LQYHVWLJDWLRQV DQG WKH PLVVSHFLILHG PRGHO LQYHVWLJDWLRQV 6Hn OHFWHG $5( HYDOXDWLRQV WKDW DUH LQGLFDWLYH RI VRPH REVHUYHG SDWWHUQV DUH UHSRUWHG

PAGE 132

EHORZ )RU XQFHQVRUHG GDWD D FORVHG IRUP H[SUHVVLRQ RI ERWK W\SHV RI $5( ZDV DOn ZD\V REWDLQHG ,Q WKH SUHVHQFH RI FHQVRULQJ KRZHYHU WKH $5( H[SUHVVLRQV JHQHUDOO\ UHTXLUHG QXPHULFDO LQWHJUDWLRQ 1RUPDO GLVWULEXWLRQ 7R LOOXVWUDWH WKH IXOO UDQJH RI $5( HYDOXDWLRQV WKDW ZHUH SHUIRUPHG FRQVLGHU 7DEOHV DQG EHORZ 5HFDOO WKDW WKH $5( HYDOXDWLRQV IRU XQFHQVRUHG GDWD DUH JLYHQ LQ 7DEOHV DQG LQ 6HFWLRQ RI WKLV PDQXVFULSW ,Q 7DEOH $r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f VR WKLV SODFH LV RPLWWHG IRU WKH WDEOH /DVWO\ WKH HIILFLHQF\ YDOXHV LQ 7DEOH DUH fV\PPHWULFf LQ WKH VHQVH WKDW WKH $5( LV WKH VDPH ZKHWKHU WKH YDOXH RI $ LV XQGHUVSHFLILHG RU RYHUVSHFLILHG 7KXV WKH EODQN VSDFHV LQ WKH WKH LWK FROXPQ DQG MWK URZ FDQ EH ILOOHG LQ ZLWK WKH HIILFLHQF\ YDOXH IURP WKH MWK FROXPQ DQG WK URZ 7KHUH DUH WZR SDWWHUQV RI WKH $5( YDOXHV LQ 7DEOH WKDW DSSHDU FRPPRQ WR DOO WKH GLVWULEXWLRQV WKDW DUH VHOHFWHG LQ WKH UHPDLQGHU RI WKLV VHFWLRQ

PAGE 133

7DEOH 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG QRUPDO GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b $W $FL f f f f f f f f f f &HQVRULQJ UDWH LV b $W $FWL f f f f f f f f f f

PAGE 134

7DEOH FRQWLQXHG &HQVRULQJ UDWH LV b $ $ FK f f f f f f f f f f $V WKH FHQVRULQJ UDWH ULVHV WKH SHQDOW\ IRU PLVVSHFLI\LQJ $ GHFUHDVHV &RPn SDULVRQ RI 7DEOH ZLWK WKH b FHQVRULQJ UDWH RI 7DEOH LQGLFDWHV WKLV IHDWXUH DV ZHOOf 7KH $5( YDOXHV XQGHU XQLIRUP FHQVRULQJ DUH DW OHDVW DV ODUJH DV WKH $5( YDOXHV XQGHU H[SRQHQWLDO FHQVRULQJ 1RWLFH IRU WKH PL[HG QRUPDO GLVWULEXWLRQ WKDW WKH $5( YDOXHV XQGHU XQLIRUP FHQn VRULQJ DUH FOHDUO\ KLJKHU WKDQ WKH $5( YDOXHV XQGHU H[SRQHQWLDO FHQVRULQJ 7DEOH DGGUHVVHV PRGHO PLVVSHFLILFDWLRQ E\ GLVSOD\LQJ $5( YDOXHV RI XVLQJ WKH ORFDWLRQVKLIW PRGHO WHVW LQVWHDG RI WKH PL[HGPRGHO WHVW 7KH ORFDWLRQVKLIW PRGHO WHVW FDQ EH UHJDUGHG DV D FHQVRUHG GDWD H[WHQVLRQ RI WKH QRUPDO VFRUHV WHVW $V LQ 7DEOH WKH IHDWXUH RI OHVV SHQDOW\ LQ $5( WHUPV DV WKH FHQVRULQJ UDWH

PAGE 135

7DEOH 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG QRUPDO GLVWULEXWLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQn WKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f

PAGE 136

LQFUHDVHV LV HYLGHQW $ FRPSDULVRQ RI 7DEOH ZLWK WKH b FHQVRULQJ UDWH RI 7DEOH LV FRQVLVWHQW ZLWK WKLV SDWWHUQ DV ZHOO /RJLVWLF GLVWULEXWLRQ :KHQ WKHUH LV QR FHQVRULQJ HYDOXDWLRQ RI WKH HIILFLHQF\ H[SUHVVLRQ LQ 7KHRUHP RU DW f JLYHV HII$FO $f H$$FK>H$$FK$W B DFLf H$Fnr f§ H$n@ H$&K f§ H$_ f IRU WKH PL[HGPRGHO ORJLVWLF VFRUHV DQG WKH PLVVSHFLILFDWLRQ RI $ SUREOHP 7KLV ODVW H[SUHVVLRQ LV DUULYHG DW E\ VWUDLJKWIRUZDUG EXW WHGLRXV DOJHEUD 6XEVWLWXWLQJ $FK f§ $ s F ZKHUH F WKH ODVW HIILFLHQF\ H[SUHVVLRQ IRU XQFHQVRUHG GDWD EHFRPHV HII$FL $f H0>H_F_ B _F_H_F_ B LMV HOG Of 7KXV WKH $5( IRU PLVVSHFLILHG $ RQO\ GHSHQGV RQ WKH DEVROXWH GLIIHUHQFH EHWZHHQ $ DQG $F DQG QRW RQ WKH DFWXDO YDOXHV WKHPVHOYHV 7DEOH GLVSOD\V WKH $5( YDOXHV IRU VRPH VHOHFWHG YDOXHV RI _F_ 7KH HIILFLHQFLHV IRU PLVVSHFLILHG $ ZKHQ WKH GDWD DUH VXEMHFW WR FHQVRULQJ GR QRW H[KLELW WKH VDPH IHDWXUH DV WKDW IRU WKH XQFHQVRUHG GDWD 7DEOH FRQWDLQV $5( YDOXHV IRU D b FHQVRULQJ UDWH 7KH YDOXHV DUH YHU\ VLPLODU XQGHU H[SRQHQWLDO RU XQLIRUP FHQVRULQJ IRU WKH b DQG b FHQVRULQJ UDWHV DV ZHOO $V PHQWLRQHG LQ WKH PL[HGQRUPDO H[DPSOH WKH FKDUDFWHULVWLF RI WKH SHQDOW\ RI PLVVSHFLI\LQJ $ GHFUHDVLQJ DV WKH FHQVRULQJ UDWH JRHV XS DOVR RFFXUV IRU WKH PL[HGORJLVWLF GLVUWLEX WLRQ

PAGE 137

7DEOH 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK QR FHQVRULQJ ?F? $5( 7DEOH 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK H[SRQHQWLDO RU XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b $W $FL f f f f f f f f f f

PAGE 138

7DEOH 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG ORJLVWLF GLVWULEXWLRQ ZLWK DEVHQFH RU SUHVHQFH RI H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b 1R $ IRU PL[HGPRGHO &HQVRULQJf VFRUH &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f 7DEOH UHSRUWV UHVXOWV IRU PRGHO PLVVSHFLILFDWLRQ 7KH ORFDWLRQVKLIW PRGHO WHVW LV WKH 3HWR3HWR JHQHUDOL]DWLRQ RI WKH :LOFR[RQ UDQN VXP WHVW 7DEOH LQGLn FDWHV WKDW IRU XQFHQVRUHG GDWD WKH :LOFR[RQ SHUIRUPV UHODWLYHO\ ZHOO WR WKH PL[HG PRGHO WHVW IRU YDOXHV RI $ XS WR $JDLQ WKH SHQDOW\ IRU PRGHO PLVVSHFLILFDWLRQ GHFUHDVHV IRU WKH $5( DV WKH FHQVRULQJ UDWH LQFUHDVHV 7KH $5( YDOXHV DUH VLPLODU XQGHU H[SRQHQWLDO RU XQLIRUP FHQVRULQJ ([WUHPH9DOXH GLVWULEXWLRQ 7DEOH GLVSOD\V $5( YDOXHV IRU PLVVSHFLILHG $ 7KH XQFHQVRUHG WKH b FHQVRULQJ UDWH DQG WKH b FHQVRULQJ UDWH FDVHV H[KLELW WKH VDPH SDWWHUQV DQG

PAGE 139

7DEOH 3LWPDQ $5( IRU PLVVSHFLILHG $ XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXn WLRQ ZLWK H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b $W $FL f f f f f f f f f f DUH WKXV QRW LQFOXGHG ,Q 6HFWLRQ ZH PHQWLRQHG WKDW WKH XQFHQVRUHG VFRUH IXQFWLRQ "!PHYXf ZDV GHULYHG XQGHU D /HKPDQQDOWHUQDWLYH W\SH RI PL[WXUH PRGHO E\ &RQRYHU DQG 6DOVEXUJ f 7KHLU SDSHU EDVHG WKH UHFRPPHQGDWLRQ RI VFRUHV ZLWK D RU HTXLYDOHQWO\ $ ORJf a RQ HIILFLHQFLHV FRPSXWHG IRU PRGHO PLVVSHFLILFDWLRQ 7KH ORFDWLRQVKLIW PRGHO WHVW XVHG E\ &RQRYHU DQG 6DOVEXUJ f LV EDVHG RQ WKH H[WUHPHYDOXH GHQVLW\ DW f ZKLFK ZH XVHG WR JHQHUDWH A!PHYZf DQG rPHYZf 7KLV ORFDWLRQVKLIW PRGHO WHVW RI &RQRYHU DQG 6DOVEXUJ f FRQVLVWV RI fLQYHUVH 6DYDJH VFRUHVf DV RSSRVHG WR WKH 6DYDJH f VFRUHV WKDW FRPSULVH WKH XQFHQVRUHG GDWD YHUVLRQ RI WKH ORJUDQN VWDWLVWLF 6LQFH WKH ORJUDQN WHVW VWDWLVWLF LV FRPPRQO\ XVHG IRU FRPSDULQJ JURXSV ZLWK UHVSHFW WR VXUYLYDO GDWD 7DEOH GLVSOD\V $5( YDOXHV IRU FRPSDULQJ WKH ORJ

PAGE 140

UDQN WHVW WR WKH PL[HGPRGHO WHVW EDVHG RQ APHYZf DQG 0(YQf ,Q FRPSXWLQJ WKH $5( YDOXHV WKH XQGHUO\LQJ VXUYLYDO GLVWULEXWLRQ ZDV DVVXPHG WR EH RI WKH IRUP f ,W LV QRWHG KRZHYHU WKDW DOWKRXJK YDOXHV DUH QRW GLVSOD\HG KHUH WKH FDOFXODWLRQV ZLWK WKH DVVXPSWLRQ RI WKH H[WUHPHYDOXH GHQVLW\ IRUP DW f OHDGV WR YHU\ VLPLODU $5( YDOXHV 7KH PD[LPXP $5( YDOXHV IRU PRGHO PLVVSHFLILFDWLRQ DSSHDU WR RFFXU IRU YDOXHV RI $ EHWZHHQ DQG ZKLFK LV FRQVLVWHQW ZLWK WKH ILQGLQJV RI &RQRYHU DQG 6DOVEXUJ f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

PAGE 141

7DEOH 3LWPDQ $5( IRU ORFDWLRQPRGHO YV PL[HGPRGHO OLQHDU UDQN WHVW PL[HG H[WUHPHYDOXH GLVWULEXWLRQ ZLWK DEVHQFH RU SUHVHQFH RI H[SRn QHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ SDWWHUQV &HQVRULQJ UDWH LV b 1R $ IRU PL[HGPRGHO &HQVRULQJf VFRUH &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f &HQVRULQJ UDWH LV b $ IRU PL[HGPRGHO VFRUH f f f f f

PAGE 142

XVHG WR WHVW WKH QXOO K\SRWKHVLV + Q LQ WKH PL[WXUH PRGHO JLYHQ E\ f 7KH VLPXODWLRQV LQ WKLV VHFWLRQ HQDEOH WKH VWXG\ RI KRZ WKH SRZHUV RI WHVWV EDVHG RQ VFRUHV JHQHUDWHG IURP GLIIHUHQW IRUPV RI )[ $f FRPSDUH ZLWK HDFK RWKHU DQG FRPSDUH ZLWK WKH VWDQGDUG FHQVRUHG GDWD WHVWV WKDW GR QRW DVVXPH D PL[WXUH PRGHO EXW LQVWHDG D ORFDWLRQVKLIW PRGHO 7KH HIIHFW RI YDULRXV FHQVRULQJ GLVWULEXWLRQV RQ WKH WHVW SURFHGXUHV LV DOVR RI LQWHUHVW 'HVFULSWLRQ RI WKH 6LPXODWLRQ VWXG\ )RU WKH PL[WXUH PRGHO DW f GDWD IRU WKH WUHDWPHQW JURXS ZDV JHQHUDWHG E\ VDPSOLQJ 1? YDOXHV IURP )[f DOVR VDPSOLQJ 1L YDOXHV IURP )[ $f DQG FKRRVLQJ WKH MWK REVHUYDWLRQ IURP HLWKHU WKH )[f VDPSOH RU WKH )>[ $f VDPSOH EDVHG RQ WKH RXWFRPH RI D RU UHVSHFWLYHO\ IURP DQ LQGHSHQGHQW %HUQRXOOL UDQGRP YDULDEOH 5 ZLWK SUREDELOLW\ RI VXFFHVV 7 3W5 f DV LQ f )RU WKH FRQWURO JURXS DQ LQGHSHQGHQW UDQGRP VDPSOH RI 1R REVHUYDn WLRQV IURP )[f ZDV REWDLQHG )RU GDWD VXEMHFW WR UDQGRP ULJKW FHQVRULQJ LQGHSHQGHQW UDQGRP VDPSOHV IRU WKH WUHDWPHQW JURXS DQG WKH FRQWURO JURXS ZHUH JHQHUDWHG IURP WKH VDPH GLVWULEXWLRQ FKDUDFWHUL]HG E\ /[f 7KH MWK REVHUYDWLRQ IURP /[f LQ D JURXS ZDV PDWFKHG XS ZLWK WKH MWK REVHUYDWLRQ IURP f DV GHVFULEHG LQ WKH SUHYLRXV SDUDJUDSK LQ RUGHU WR GHWHUPLQH ZKHWKHU RU QRW FHQVRULQJ KDG RFFXUUHG

PAGE 143

7KH VLJQLILFDQFH OHYHO ZDV IL[HG DW D WKURXJKRXW WKH VWXG\ 6DPSOH VL]HV RI 1R 1? DQG 1R 1? ZHUH VHOHFWHG 7KUHH VXUYLYDO GLVWULEXWLRQV IRU WKH ORJDULWKP RI WKH VXUYLYDO WLPH ZHUH FKRVHQ 1RWH WKDW DOO KDYH VXSSRUW f§ RR RRf 7KH QRUPDO GLVWULEXWLRQ FKDUDFWHUL]HG E\ )^[ $f >rr GW 9 -[ 7KH &DXFK\ GLVWULEXWLRQ )[ $f f§ DUFWDQ[ f§ $f 7KH H[WUHPHYDOXH GLVWULEXWLRQ )[ $f H[Sf§ 7KHVH WKUHH FKRLFHV RI VXUYLYDO GLVWULEXWLRQV HQDEOH HYDOXDWLRQ RI SHUIRUPDQFH E\ WKH WHVWV IRU PHGLXP DQG KHDY\ WDLOHG GLVWULEXWLRQV DV ZHOO DV D GLVWULEXWLRQ ZLWK PRGHUDWH GHSDUWXUH IURP V\PPHWU\ 7KH WZR FHQVRULQJ GLVWULEXWLRQV DV LQ 6HFWLRQ f VHOHFWHG ZHUH 7KH GLVWULEXWLRQ RI WKH QDWXUDO ORJDULWKP RI DQ H[SRQHQWLDO UDQGRP YDULDEOH ZLWK KD]DUG UDWH $ L H WKH H[WUHPHYDOXH GLVWULEXWLRQ /[f H[S[ ORJO$f JUf§ORVL$ffA FR [ 2*f $ 7KH GLVWULEXWLRQ RI WKH QDWXUDO ORJDULWKP RI D XQLIRUP UDQGRP YDULDEOH ZLWK VXSSRUW 0f L H /[f f§ H f§RR [ ORJ 0 0

PAGE 144

7KHVH WZR FHQVRULQJ GLVWULEXWLRQV KDYH EHHQ HPSOR\HG WR PRGHO WKH FHQVRULQJ PHFKn DQLVP RQ GDWD LQ D FOLQLFDO WULDO ZLWK UDQGRP VWDUWLQJ WLPHV IRU VXEMHFWV 9DOXHV RI WKH SDUDPHWHUV $ DQG 0 ZHUH VHOHFWHG LQ WKH VWXG\ WR JLYH FHQVRULQJ UDWHV RI b b DQG b XQGHU WKH QXOO K\SRWKHVLV [ 7KH VLWXDWLRQ RI QR FHQVRULQJ LH b FHQVRULQJ UDWH LV DOVR FRQVLGHUHG 1RWH WKDW RXU UHVXOWV IRU WKH b FHQVRULQJ UDWH H[WHQG WKH UHVXOWV RI WKH VLPXODWLRQ E\ -RKQVRQ HW DO f $OO SRVVLEOH FRPELQDWLRQV RI [ f DQG $ f ZHUH FRQVLGHUHG IRU SDUDPHWHU YDOXHV LQ WKH PL[WXUH PRGHO DW f ,QFOXGLQJ WKH QXOO FDVH [ WKLV \LHOGHG SDUDPHWHU VHWWLQJV IRU HDFK SRVVLEOH FRPELQDWLRQ RI VXUYLYDO IRUP )[ $f FHQVRULQJ IRUP /[f DQG FHQVRULQJ UDWH $ FRQILJXUDWLRQ LQ RXU VWXG\ UHSUHVHQWV D FRPELQDWLRQ RI $ YDOXH RI [ $ YDOXH RI $ 7KH IRUP RI )[ f§ $f 7KH IRUP RI /[f 7KH FHQVRULQJ UDWH 7KH VDPSOH VL]HV 1 DQG $7 ,Q WRWDO FRQILJXUDWLRQV WR JHQHUDWH GDWD XQGHU f ZHUH FRQVLGHUHG 5DQGRP QXPEHU IXQFWLRQV LQ 6SOXV 9HUVLRQ %HFNHU &KDPEHUV DQG :LONV 6WDWLVWLFDO 6FLHQFHV f JHQHUDWHG WKH GDWD DV GHVFULEHG DERYH $V D PHDQV

PAGE 145

RI FKHFNLQJ WKH YDOLGLW\ RI WKH UDQGRP VDPSOH JHQHUDWRU FDSDELOLWLHV RI 6SOXV ZH SORWHG VHYHUDO TT SORWV IRU RXU VDPSOHV )LJXUHV DQG VKRZ WZR VXFK SORWVf§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f ZDV DOZD\V XVHG ,I WKH YDOXH RI D WHVW VWDWLVWLF H[FHHGHG WKH QXOO K\SRWKHVLV RI U ZDV UHMHFWHG RWKHUZLVH WKH QXOO K\SRWKHVLV ZDV QRW UHMHFWHG 5HIHUHQFH WR D fWHVW VWDWLVWLFf IRU WKH UHPDLQGHU RI WKLV FKDSWHU PHDQV WKH VWDQGDUGL]HG YHUVLRQ RI WKH OLQHDU UDQN VWDWLVWLF 7KH WHVW VWDWLVWLFV LQFOXGHG WKH ORJUDQN *HKDQfV JHQHUDOL]HG :LOFR[RQ f DQG WKH 3HWR3HWR JHQHUDOL]HG :LOFR[RQ YHUVLRQ f :KHQ WKH XQGHUO\LQJ VXUn YLYDO GLVWULEXWLRQ ZDV QRUPDO DQ H[WHQGHG YHUVLRQ RI WKH QRUPDO VFRUHV WHVW VWDWLVWLF WKDW XVHV WKH FHQVRUHG VFRUH IXQFWLRQV GHULYHG IURP WKH PHWKRGV RI 3UHQWLFH f ZDV DOVR FRPSXWHG 7HVW VWDWLVWLFV EDVHG RQ PL[HGPRGHO VFRUHV GHULYHG IURP HDFK RI WKH QRUPDO ORJLVWLF H[WUHPHYDOXH GRXEOHH[SRQHQWLDO DQG &DXFK\ IRUPV RI )[ $f ZHUH DOVR FRPSXWHG $SSUR[LPDWH VFRUHV WKDW FRQVLVWHG RI VXEVWLWXWLQJ WKH VXUYLYDO IXQFWLRQ HVWLPDWH )S[f VHH f LQWR WKH XQFHQVRUHG DQG FHQVRUHG

PAGE 146

)LJXUH UDQGRP REVHUYDWLRQV IURP D QRUPDO GLVWULEXWLRQ

PAGE 147

TXDQWLOH )LJXUH UDQGRP REVHUYDWLRQV IURP DQ H[WUHPHYDOXH GLVWULEXWLRQ

PAGE 148

VFRUH IXQFWLRQV ZHUH DOZD\V XVHG 7KH YDULDQFH HVWLPDWRU 9L ZDV DOZD\V XVHG )RU FRQILJXUDWLRQV ZLWK QR FHQVRULQJ DQ fH[DFWf H[SUHVVLRQ IRU WKH YDULDQFH FRXOG KDYH EHHQ HYDOXDWHG FI 7KHRUHP f DQG HPSOR\HG +RZHYHU VLQFH VXFK D YDULDQFH H[SUHVVLRQ FI f LQ 7KHRUHP f JHQHUDOO\ GHSHQGV RQ WKH FHQVRULQJ GLVWULn EXWLRQV WKH HVWLPDWRU 9L ZDV XVHG IRU WKH SXUSRVHV RI XQLIRUPLW\ 6LQFH WKH VFRUHV GHSHQG RQ D YDOXH RI $ VFRUHV ZLWK YDOXHV RI $ DQG ZHUH FDOFXODWHG ,Q VXPPDU\ WKH IROORZLQJ VWDWLVWLFV ZHUH FDOFXODWHG IRU HDFK FRQILJXUDWLRQ f ORJUDQN GHQRWHG E\ /* f *HKDQ *+ RU : IRU :LOFR[RQ ZKHQ QR FHQVRULQJ RFFXUVf f 3HWR3HWR 33 HTXDOV *+ : ZKHQ QR FHQVRULQJ RFFXUVf f QRUPDO VFRUHV 16 RQO\ FDOFXDOWHG ZKHQ ) LV QRUPDOf f PL[HG QRUPDO ZLWK $ GHQRWHG E\ 01f f PL[HG QRUPDO ZLWK $ 01f f PL[HG QRUPDO ZLWK $ 01f f PL[HG ORJLVWLF ZLWK $ 0/f f PL[HG ORJLVWLF ZLWK $ 0/f f PL[HG ORJLVWLF ZLWK $ 0/f f PL[HG H[WUHPHYDOXH ZLWK $ 0(9Of f PL[HG H[WUHPHYDOXH ZLWK $ 0(9f

PAGE 149

f PL[HG H[WUHPHYDOXH ZLWK $ 0(9f f PL[HG GRXEOHH[SRQHQWLDO ZLWK $ 0'(Of f PL[HG GRXEOHH[SRQHQWLDO ZLWK $ 0'(f f PL[HG GRXEOHH[SRQHQWLDO ZLWK $ 0'(f f PL[HG &DXFK\ ZLWK $ 0&f f PL[HG &DXFK\ ZLWK $ 0&f f PL[HG &DXFK\ ZLWK $ 0&f $ WRWDO RI UHSHWLWLRQV ZHUH UXQ IRU HDFK FRQILJXUDWLRQ $ FRXQWHU RI WKH QXPEHU RI WLPHV WKH YDOXH RI WKH WHVW VWDWLVWLF H[FHHGHG WKH FULWLFDO YDOXH ZDV NHSW 7KH YDOXH RI WKH FRXQWHU ZDV RXWSXW DIWHU HYHU\ UHSHWLWLRQV WR SHUPLW D FKHFN WKDW WKH UDQGRP QXPEHU JHQHUDWRU ZDV QRW UHSHDWLQJ WKH VDPH F\FOH RI YDOXHV 7KH RQO\ GLUHFW FRPSDULVRQ ZLWK VLPLODU VLPXODWLRQ VWXGLHV LQ WKH OLWHUDWXUH LV ZLWK 7DEOH RI -RKQVRQ HW DO f 1HLWKHU *RRG f QRU &RQRYHU DQG 6DOVEXUJ f UHSRUW VLPXODWLRQ UHVXOWV LQ WKHLU SDSHUV DOWKRXJK WKH ODWWHU LQGLn FDWH fJRRG DJUHHPHQWf RI HPSLULFDO DQG QRPLQDO VLJQLILFDQFH OHYHOV RI WKHLU GHULYHG WHVWV XVHG ZLWK DQ DGKRF WGLVWULEXWLRQ DSSUR[LPDWLRQ %RRV DQG %URZQLH f SUHVHQW VRPH VLPXODWLRQ UHVXOWV EXW XVH YDOXHV RI U RU WR JHQHUDWH QRQUHVSRQGHUV GDWD ZLWK QR FHQVRULQJ ,Q WKH IROORZLQJ WKH UHVXOWV RI RXU VLPXODWLRQ VWXG\ ZLOO EH SUHVHQWHG LQ WKUHH SDUWV ,Q WKH ILUVW SDUW ZH ZLOO FRPSDUH RXU XQFHQVRUHG GDWD UHVXOWV RI -RKQVRQ HW

PAGE 150

DO f LQ WKRVH FDVHV ZKHUH VXFK FRPSDULVRQ LV SRVVLEOH ,Q WKH VHFRQG SDUW ZH ZLOO SUVHQW DQ RYHUDOO GLVFXVVLRQ RI RXU UHVXOWV LQ WKH XQFHQVRUHG GDWD FDVH ZKLOH WKH WKLUG SDUW ZLOO EH UHVHUYHG IRU D GLVFXVVLRQ RI FHQVRUHG GDWD UHVXOWV &RPSDULVRQ ZLWK -RKQVRQ HW DO f UHVXOWV 7DEOHV DQG GLVSOD\ D FRPSDULVRQ RI UHVXOWV IURP FRPPRQ FRQILJXUDWLRQV EHWZHHQ RXU VLPXODWLRQV DQG VRPH RI WKH VLPXODWLRQ ILJXUHV UHSRUWHG LQ 7DEOH RI -RKQVRQ HW DO f 5HFDOO WKDW WKH VWDWLVWLFV *+ 33 DQG : DUH WKH VDPH KHUH EHFDXVH WKHUH LV QR FHQVRULQJ )HDWXUHV LQ FRPPRQ IRU WKH ERWK VLPXODWLRQV LQFOXGH 7KHUH LV QR FHQVRULQJ 7KH XQGHUO\LQJ GLVWULEXWLRQ J[ LU $f LV PL[HG QRUPDO $ ODUJH VDPSOH DSSUR[LPDWLRQ LV XVHG 3RZHUV RI WKH WHVWV ZHUH HVWLPDWHG XVLQJ WULDOV 6DPSOH VL]HV RI 1R 1? ZHUH XVHG $OO SRVVLEOH FRPELQDWLRQV RI SDUDPHWHU YDOXHV $ f DQG W f DV ZHOO DV WKH QXOO W FDVH ZHUH FRQVLGHUHG 7KH GLIIHUHQFHV LQ IHDWXUHV DUH -RKQVRQ HW DO f XVH D GLIIHUHQW YDULDQFH HVWLPDWRU RI X 6DPSOH VL]HV RI 1R 1L ZHUH HPSOR\HG LQ RXU VLPXODWLRQ ZKHUHDV -RKQVRQ HW DO f XVHG 1R 1L

PAGE 151

7KH VLJQLILFDQFH OHYHOV ZHUH HVWLPDWHG IURP WULDOV LQ -RKQVRQ HW DO f RXU HVWLPDWHG OHYHOV ZHUH EDVHG RQ WULDOV 7DEOH JLYHV WKH PRVW GLUHFW FRPSDULVRQ EHWZHHQ WKH VLPXODWLRQ RI -RKQVRQ HW DO f DQG RXUV EHFDXVH 1R 1L ,Q RXU VWXG\ WKH DELOLW\ RI D WHVW VWDWLVWLF WR KROG WKH QRPLQDO OHYHO RI D ZDV DVFHUWDLQHG RQ WKH EDVLV RI WKH LQWHUYDO s f 6( ZKHUH 6( Iff m ,I WKH HPSLULFDO VL]HV IHOO RXWVLGH WKH LQWHUYDO RI f WKHUH LV HYLGHQFH WKDW WKH FRUUHVSRQGLQJ WHVW VWDWLVWLF GRHV QRW KROG WKH QRPLQDO YDOXH RI D ,W VKRXOG DOVR EH NHSW LQ PLQG KRZHYHU WKDW WKH FKRVHQ VDPSOH VL]HV PD\ QRW EH ODUJH HQRXJK WR LQVXUH DV\PSWRWLF QRUPDOLW\ RI D JLYHQ WHVW VWDWLVWLF :LWK WKLV FULWHULRQ QRQH RI WKH HVWLPDWHG VL]HV LQ 7DEOH VLJQLILFDQWO\ GLIIHU IURP DOWKRXJK 01f LV FORVH )RU WKH DOWHUQDWLYH FRQILJXUDWLRQV WKH PRVW VWULNLQJ SDWWHUQ LV WKDW WKH 01f WHVW LQ RXU VLPXODWLRQ FRQVLVWHQWO\ KDV KLJKHU SRZHU WKDQ WKH YHUVLRQ RI 01f LQ -RKQVRQ HW DO f 7KHUH LV DOVR D SDWWHUQ RI WKH 01f : DQG 16 VWDWLVWLFV KDYLQJ HPSLULFDO SRZHUV FOHDUO\ DERYH -RKQVRQ HW DO f ZKHQ [ RU DQG WKH XQGHUO\LQJ GLVWULEXWLRQ KDV $ +RZHYHU ERWK WKH 16 DQG : WHVW VWDWLVWLFV DSSHDU LQ DJUHHPHQW ZLWK WKHLU -RKQVRQ HW DO f FRXQWHUSDUWV ZKHQ [ 7KH GLIIHUHQFH LQ YDULDQFH HVWLPDWRUV ZKHQ 1 1? IRU RXU WHVW SURFHGXUHV

PAGE 152

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI 1S 1L 7 7 7 7 $$$ 7HVW 6L]H : f f f f f f f f f f 16 f f f f f f f f f f 01f f f f f f f f f f f 01f f f f f f f f f f f $OO WKH QXPEHUV LQ SDUHQWKHVHV DUH WDNHQ IURP 7DEOH RI -RKQVRQ HW DO f

PAGE 153

DV FRPSDUHG ZLWK -RKQVRQ HW DO f FRXOG EH D UHDVRQ IRU WKH GLVSDULWLHV ZKHQ ODUJHU YDOXHV RI $ IRU HLWKHU WKH XQGHUO\LQJ GLVWULEXWLRQ RU WKH PL[HG QRUPDO VFRUHV DUH FKRVHQ ,W LV LQWHUHVWLQJ WKDW IRU WKH : 16 DQG 01f VWDWLVWLFV RXU HPSLULFDO OHYHOV ZHUH ORZHU WKDQ -RKQVRQ HW DO f ZKLOH XQGHU WKH DOWHUQDWLYH FRQILJXUDn WLRQV RXU YHUVLRQV WHQGHG WR KDYH KLJKHU SRZHU WKDQ WKRVH YHUVLRQV RI -RKQVRQ HW DO f 7DEOH FRQWUDVWV RXU UHVXOWV IRU PL[HG QRUPDO GLVWULEXWLRQV ZLWK QR FHQVRULQJ DQG VDPSOH VL]HV 1 1[ ZLWK WKH FRUUHVSRQGLQJ UHVXOWV RI -RKQVRQ HW DO f IRU VDPSOH VL]HV RI 1R 1L 7KH VL]HV IRU : 16 DQG 01f DUH LQ EHWWHU DJUHHPHQW WKDQ LQ 7DEOH SHUKDSV GXH WR EHWWHU DJUHHPHQW RI RXU YDULDQFH HVWLPDWHV DQG WKH YDULDQFH HVWLPDWHV RI -RKQVRQ HW DO f IRU ODUJHU VDPSOH VL]HV 7KH UHVXOWV DUH VLPLODU WR -RKQVRQ HW DO f H[FHSW WKDW RXU WHVW VWDWLVWLF YHUVLRQV DJDLQ VHHP WR KDYH VOLJKWO\ HOHYDWHG SRZHU SHUKDSV SDUWO\ GXH WR WKH GLIIHUHQFH LQ VDPSOH VL]HV 2XU 01f VWDWLVWLF DSSHDUV OLEHUDO E\ WKH FULWHULRQ RI VLJQLILFDQWO\ H[FHHGLQJ WKH QRPLQDO OHYHO RI 6LPXODWLRQ 5HVXOWV LQ WKH 8QFHQVRUHG GDWD FDVH 7KH FRPSOHWH UDQJH RI UHVXOWV RI RXU VLPXODWLRQ VWXG\ RQ WKH WHVW VWDWLVWLFV ZKHQ WKHUH LV QR FHQVRULQJ RI WKH GDWD LV QRZ GLVFXVVHG 5HFDOO WKH WKUHH W\SHV RI XQGHUO\LQJ GLVWULEXWLRQV VHOHFWHGf§QRUPDO &DXFK\ DQG H[WUHPHYDOXH ,Q WKH IROORZLQJ ZH SUHVHQW VRPH W\SLFDO UHVXOWV RI WKH SDWWHUQV WKDW ZHUH REVHUYHG IURP XQFHQVRUHG GDWD LQ WKH VLPXODWLRQ VWXG\ $ OLVWLQJ RI WKHVH SDWWHUQV IRU XQFHQVRUHG GDWD LV

PAGE 154

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG QR FHQVRULQJ ZLWK JURXS VDPSOH VL]HV RI f 1S 0 -9 1 f ; f§ 4 7 ; ; $$$ 7HVW 6L]H : f f f f f f f f f f 16 f f f f f f f f f f 01f f f f f f f f f f f 01f f f f f f f f f f f $OO WKH QXPEHUV LQ SDUHQWKHVHV DUH WDNHQ IURP 7DEOH RI -RKQVRQ HW DO f

PAGE 155

$V WKH FKRVHQ $ YDOXH IRU D PL[HGPRGHO VFRUH JHWV ODUJHU WKH SRZHU RI WKH FRUUHVSRQGLQJ WHVW DOVR JHWV ODUJHU )RU JURXS VDPSOH VL]HV RI DOO PL[HGPRGHO VFRUH WHVWV KROG QRPLQDO VLJQLILn FDQFH OHYHOV IDLUO\ ZHOO H[FHSW IRU WKH PL[HGQRUPDO EDVHG WHVWV ZLWK VWDWLVWLFV 01f DQG 01f :KHQ JURXS VDPSOH VL]HV DUH WKH PL[HGPRGHO VFRUH WHVWV EDVHG RQ $ RU $ KROG WKH QRPLQDO D H[FHSW IRU WKH QRUPDO FDVH 01f 7KH 0/f 0(9f DQG 01f FRQVLVWHQWO\ KDG KLJK SRZHUV RYHU WKH FRQn ILJXUDWLRQV VWXGLHG :H QRZ ORRN DW WKH H[LVWHQFH RI WKHVH SDWWHUQV IRU VRPH H[DPSOH FRQILJXUDWLRQV LQ RXU VLPXODWLRQ VWXG\ )RU SXUSRVHV RI LOOXVWUDWLRQ 7DEOH GLVSOD\V WKH FRPSOHWH VHW RI ILJXUHV REn WDLQHG IURP D SDUWLFXODU FRPELQDWLRQ RI f 6DPSOH VL]H 1 1? f 6XUYLYDO GLVWULEXWLRQ H[WUHPHYDOXH f &HQVRULQJ GLVWULEXWLRQ 1RQH RU WHFKQLFDOO\ /[f IRU DOO [f f &HQVRULQJ UDWH b 5HFDOO IURP 6HFWLRQ WKDW WKH VFRUH IXQFWLRQV LQ WKH 0(9 f VWDWLVWLFV LQ 7DEOH DUH QRW GHULYHG IURP WKH H[WUHPHYDOXH IRUP RI WKH XQGHUO\LQJ GLVWULEXWLRQ LH WKH ORJDULWKP RI DQ H[SRQHQWLDO UDQGRP YDULDEOH 5DWKHU WKH VFRUHV DUH GHULYHG

PAGE 156

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG QR FHQn VRULQJ ZLWK JURXS VDPSOH VL]HV RI 1 1; 7 f§ 7 U 7 $ $ $ 7HVW 6L]H /* *+ 33 01f 01f 01 0/f 0/f 0/f 0(9Of 0(9f 0(9 0'(Of 0'(f 0'( 0&f 0&f 0&f

PAGE 157

IURP DQ H[WUHPHYDOXH IRUP ZLWK D GHQVLW\ DFKLHYHG E\ WDNLQJ WKH ORJDULWKP RI WKH LQYHUVH RI DQ H[SRQHQWLDO UDQGRP YDULDEOH +HQFH WKH 0(9 f VWDWLVWLFV ZLOO QRW QHFHVVDULO\ WHQG WR SHUIRUP WKH EHVW RXW RI WKH PL[HGPRGHO WHVWV LQ WHUPV RI SRZHU DQG PDLQWDLQLQJ D %XW WKH VLPLODULW\ RI WKH H[WUHPHYDOXH IRUPV OLNHO\ DOORZV WKH JRRG FRQVLVWHQW SHUIRUPDQFH RI WKH 0(9 f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f§ DV 1 f§ RR 7KH ODFN RI D SRZHU ORVV IRU PLVVSHFLILHG $ IHDWXUHG LQ 7DEOH DQG LQ RWKHU VLPXODWLRQV FRQGXFWHG LQ RXU VWXG\ LV QRW XQLTXHf§7DEOH RI -RKQVRQ HW DO f H[KLELWV WKH VDPH IHDWXUH WR VRPH GHJUHH DV ZHOO 0RVW RI WKH WHVW VWDWLVWLFV LQ 7DEOH KDYH VLJQLILFDQFH OHYHOV WKDW OLH ZLWKLQ WZR VWDQGDUG HUURUV RI 7KH 01f DQG 01f HPSLULFDO VLJQLILFDQFH OHYHOV IDOO ZHOO DERYH WZR VWDQGDUG HUURUV DZD\ IURP WKHUHE\ VXJJHVWLQJ WKDW WKH WHVW DVVRFLDWHG ZLWK WKHVH VWDWLVWLFV WHQG WR EH OLEHUDO 7KH 01f DQG 01f VWDWLVWLFV GR GLVSOD\ WKH KLJKHVW SRZHUV IRU GHWHFWLQJ WKH YDULRXV DOWHUQDWLYH FDVHV

PAGE 158

$PRQJ WKRVH WHVW VWDWLVWLFV WKDW PDLQWDLQ WKH QRPLQDO VLJQLILFDQFH OHYHOV 01f 0/f 0(9f DQG 0'(f KDYH VXSHULRU SRZHU 7KH SRZHU YDOXHV RI WKH VWDQn GDUG /* WHVW VWDWLVWLF JDLQ JURXQG DV LU JHWV ODUJHU EXW WKH *+ 33 : VWDWLVWLF SHUIRUPV SRRUO\ WKURXJKRXW 7KH VWDWLVWLF 0'(f KDV WKH KLJKHVW SRZHU YDOXHV IRU WKH PRVW DOWHUQDWLYH VHWWLQJV ZKLOH 0/f KDG WKH VHFRQG KLJKHVW 7KH 0/f VLJn QLILFDQFH OHYHO GRHV KDYH DQ HGJH f RYHU WKH 0'(f VLJQLILFDQFH OHYHO f $OVR QRWH WKDW WKH SRZHU YDOXHV RI 0(9f ZHUH FRQWLQXDOO\ FORVH EHKLQG WKRVH RI 0/f 7KH 0/f DQG 0(9f VWDWLVWLFV GR IDLUO\ ZHOO LQ FRPSDULVRQ WR 0/f DQG 0(9f :KHQ 1 1? IRU WKH H[WUHPHYDOXHQR FHQVRULQJ FRQILJXUDWLRQ WKH PL[HG PRGHO WHVW VWDWLVWLFV ZLWK VFRUHV EDVHG RQ $ RU FRQVLVWHQWO\ KDYH KLJK VLJQLILFDQFH OHYHOV 7KH WHVW VWDWLVWLFV XVLQJ $ LQ WKHLU VFRUHV DOO KDG VLJQLILFDQFH OHYHOV RI RU KLJKHU DQG WKXV ZHUH QRW LQFOXGHG LQ 7DEOH 7KH 0'(f VWDWLVWLF ZLWK D VLJQLILFDQFH OHYHO RI SRVVHVVHV WKH KLJKHU SRZHU ILJXUHV RXW RI WKRVH OLVWHG 1RWH WKDW WKH /* SHUIRUPV EHWWHU WKDQ WKH 0/f DQG 0(9Of VWDWLVWLFV LQ WHUPV RI SRZHU 7KH WHQGHQF\ RI OLEHUDO WHVWV DQG LQFUHDVHG SRZHU DOVR VKRZHG XS LQ VLPXODWLRQV ZKHQ WKH XQGHUO\LQJ VXUYLYDO GLVWULEXWLRQ ZDV PL[HG QRUPDO 7DEOHV DQG SURYLGHG XV ZLWK D VXEVHW RI WKH UHVXOWV WKDW ZDV SUHYLRXVO\ GLVFXVVHG ,Q FRPSDULVRQ ZLWK WKH RWKHU PL[HGPRGHO WHVWV DQG WKH /* DQG 16 VWDWLVWLFV WKH 01f GLG ZHOO LQ WHUPV RI PDLQWDLQLQJ WKH VLJQLILFDQFH OHYHO DQG GHWHFWLQJ DOWHUQDWLYH YDOXHV RI LU ZKHQ WKH JURXS VDPSOHV VL]HV ZHUH RU

PAGE 159

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG QR FHQn VRULQJ ZLWK JURXS VDPSOH VL]HV RI 1R 1[ [ [ [ [ $$$ 7HVW 6L]H /* 01f 0/f 0/f 0(9Of 0(9f 0'(f

PAGE 160

7KH SRZHUV RI DOO WKH WHVWV LQFOXGHG LQ RXU VLPXODWLRQV ZHUH ORZ IRU D KHDY\ WDLOHG &DXFK\ VXUYLYDO GLVWULEXWLRQ )LJXUHV DUH QRW GLVSOD\HG IRU WKH VDNH RI EUHYLW\ 7KH 0&f DQG 0&f FRQVLVWHQWO\ KDG WKH EHVW SRZHU YDOXHV UHODWLYH WR WKH RWKHU WHVW VWDWLVWLFV $PRQJ WKHVH RWKHUV WKH 0'(Of WHVW VWDWLVWLF SHUIRUPHG WKH EHVW 7KHUH ZDV D VKDUS GURSRII WR WKH SRZHU ILJXUHV IRU 0'(f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f SHUIRUPV ZHOO UHODWLYH WR WKH PL[HGPRGHO WHVWV IRU VPDOOHU YDOXHV RI $ HJ $ f LQ WKH XQGHUO\LQJ GLVWULEXWLRQ RU ZKHQ WKH FHQVRULQJ UDWH EHFRPHV KHDY\ ,W YLUWXDOO\ DOZD\V KDV JUHDWHU SRZHU WKDQ WKH *HKDQ *+f DQG 3HWR3HWR 33f VWDWLVWLFV 0L[HGPRGHO VFRUH WHVWV FRQVLVWHQWO\ KDYH EHWWHU SRZHU WKDQ WKH ORJUDQN WHVW ZKHQ WKH XQGHUO\LQJ GLVWULEXWLRQ KDV WKH VHWWLQJV $ RU $ :KHQ WKH FHQVRULQJ UDWH LV VPDOO WR PRGHUDWH HJ bf DQG $ WKH 0/f 0(9f DQG 01f DUH EHVW DPRQJ WKH PL[HGPRGHO WHVWV VWXGLHG

PAGE 161

LQ WKH VHQVH RI VLPLODU SRZHU DQG KROGLQJ QRPLQDO VLJQLILFDQFH OHYHOV RYHU WKH ZLGH YDULHW\ RI FHQVRULQJ DQG VXUYLYDO GLVWULEXWLRQV FRQVLGHUHG )RU KHDY\WDLOHG GLVWULEXWLRQV DQG VPDOO VDPSOH VL]HV DOO WKH WHVWV JHQHUDOO\ H[FHHG WKH QRPLQDO OHYHO D 7KH PL[HGPRGHO WHVWV EDVHG RQ &DXFK\ VFRUHV DUH JHQHUDOO\ ZHDN LQ SRZHU DQG DUH FKDOOHQJHG E\ WKH *+ DQG 33 VWDWLVWLFV LQ OLPLWHG LQVWDQFHV ZKHUH WKH QRUPDO DSSUR[LPDWLRQ RI WKH GLVWULn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b DQG ERWK H[SRQHQWLDO DQG XQLIRUP FHQVRULQJ GLVWULEXWLRQV DUH JLYHQ LQ 7DEOH 7KH 0'(f 01f DQG 01f VWDWLVWLFV UHVXOWV QRW GLVSOD\HGf KDG VLJQLILFDQFH OHYHOV RI RU JUHDWHU )RU WKH UHVW RI WKH VWDWLVWLFV XQGHU FRQVLGHUDWLRQ WKH 0/f DQG 0(9f VWDWLVWLFV FOHDUO\ KDG WKH KLJKHVW SRZn HUV ZLWK 0/f DQG 0(9f GRLQJ ZHOO LQ FRPSDULVRQ 7KHUH DSSHDU WR EH QR PDUNHG GLIIHUHQFHV IRU WKH SRZHUV GXH WR ZKHWKHU WKH FHQVRULQJ GLVWULEXWLRQ IRUP ZDV H[SRQHQWLDO RU XQLIRUP

PAGE 162

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI 1 1c ([SRQHQWLDO DQG 8QLIRUP &HQVRULQJ 'LVWULEXWLRQV ; 7 ; ; $$$ 7HVW 6L]H /* f f f f f f f f f f 01f f f f f f f f f f f 0/f f f f f f f f f f f 0/f f f f f f f f f f f 0(9f f f f f f f f f f f 0(9f f f f f f f f f f f

PAGE 163

7DEOH LQGLFDWHV D OHVV FOHDU SLFWXUH ZKHQ WKH FHQVRULQJ UDWH LV D PRGHUDWH b 7KH 0/f DQG 0(9f VWDWLVWLFV KDYH KLJK VLJQLILFDQFH OHYHOV XQGHU XQLIRUP FHQVRULQJ EXW QRW XQGHU H[SRQHQWLDO FHQVRULQJ ZKHUH LQWHUHVWLQJO\ 0/f DQG 0(9f KDYH KLJKHU VLJQLILFDQFH OHYHOV 7KH 01f DQG 01f VWDWLVWLFV EHKDYH VLPLODUO\ 7KH /* 01f 0/f 0(9f DQG 0'(f DUH SUHIHUDEOH VLQFH WKH\ PDLQWDLQ D DQG KDYH FRPSDUDEOH SRZHU 7KH HIIHFW RI D XQLIRUP FHQVRULQJ GLVWULEXWLRQ LV PRUH SURQRXQFHG IRU D FHQVRUn LQJ UDWH RI b $OO RI WKH WHVW VWDWLVWLFV LQ WKH VWXG\ KDG HVWLPDWHG VLJQLILFDQFH OHYHOV RI RU KLJKHU XQGHU XQLIRUP FHQVRULQJ ZLWK PRVW RI WKHP IDOOLQJ WKUHH VWDQGDUG HUURUV RU PRUH DERYH 2Q WKH RWKHU KDQG DOO RI WKH WHVW VWDWLVWLFV KDG VLJQLILFDQFH YDOXHV RI RU OHVV XQGHU H[SRQHQWLDO FHQVRULQJ WKDW LV YDOXHV ZLWKLQ WZR VWDQGDUG HUURUV RI 5HVXOWV DUH QRW GLVSOD\HG KHUH EXW DJDLQ /* 01f 0/f 0(9f DQG 0'(f ZHUH PRVW DSSHDOLQJ LQ WHUPV RI EDODQFLQJ JRRG SRZHU XQGHU DOWHUQDWLYH SDUDPHWHU VHWWLQJV DORQJ ZLWK PDLQWHQDQFH RI WKH QRPLQDO D 5HVXOWV IRU DQ XQGHUO\LQJ H[WUHPHYDOXH GLVWULEXWLRQ 1R 1L DQG WKH SUHVHQFH RI FHQVRULQJ DUH QRW GLVSOD\HG EXW LQ VXPPDU\ IRU H[SRQHQWLDO FHQVRULQJ WKH 01f 0/f 0(9f DQG 0'(f VWDWLVWLFV DOO SHUIRUPHG WKH EHVW IRU ERWK WKH b DQG b FHQVRULQJ UDWHV 7KH /* VWDWLVWLF DJDLQ ZDV D ZRUWKZKLOH FRPSHWLn WRU EXW WKH SRZHU ILJXUHV ZHUH QRW DV QHDUO\ FORVH WR WKH PL[HGPRGHO FRXQWHUSDUWV DV LQ WKH XQLIRUP FHQVRULQJ FDVH 8QGHU XQLIRUP FHQVRULQJ RQO\ WHVW VWDWLVWLFV KDY } LQJ PL[HGPRGHO VFRUHV ZLWK $ PDLQWDLQHG UHDVRQDEOH VLJQLILFDQFH OHYHOV IRU

PAGE 164

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG H[WUHPHYDOXH GLVWULEXWLRQ DQG b H[SRQHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI 1S 1? ([SRQHQWLDO DQG 8QLIRUP &HQVRULQJ 'LVWULEXWLRQV 7 7 f§ ,, R WR ,, 2 &2 $ $ $ 7HVW 6L]H /* f f f f f f f f f f 01f f f f f f f f f f f 01f f f f f f f f f f f 0/f f f f f f f f f f f 0/f f f f f f f f f f f 0(9f f f f f f f f f f f 0(9f f f f f f f f f f f 0'(f f f f f f f f f f f 0'(f f f f f f f f f f f

PAGE 165

ERWK WKH b DQG b FHQVRULQJ UDWHV 7KH /* VWDWLVWLF KDG FRPSDUDEO\ KLJK YDOXHV DURXQG 3RZHUV XQGHU DOWHUQDWLYH SDUDPHWHU VHWWLQJV ZHUH VLPLODU IRU 01f 0/f 0(9Of DQG 0'(Of 7KH /* VWDWLVWLF FRPSDUHG YHU\ ZHOO ZLWK WKHVH PL[HGPRGHO WHVWV $ VLPXODWLRQ ZLWK b FHQVRULQJ UDWH ZDV QRW DWWHPSWHG IRU VDPSOH VL]HV RI VLQFH WKH ILJXUHV IURP WKH ORZHU FHQVRULQJ UDWHV LQGLFDWHG WKDW WKH DV\PSWRWLF GLVWULEXWLRQV RI WKH WHVW VWDWLVWLFV ZHUH VXVSHFW XQGHU XQLIRUP FHQVRULQJ 'HSHQGHQFH RQ WKH FHQVRULQJ GLVWULEXWLRQ ZDV DOVR DSSDUHQW IRU WKH SHUIRUPDQFH RI WKH PL[HGPRGHO WHVW VWDWLVWLFV ZKHQ WKH XQGHUO\LQJ VXUYLYDO GLVWULEXWLRQ ZDV QRUPDO $JDLQ IRU D b FHQVRULQJ UDWH DQG 1R 1? WKH 01f DQG 01f VWDWLVWLFV KDG VLJQLILFDQFH OHYHOV UDQJLQJ IURP WR 7KH UHVXOWV IRU WKH b FHQVRULQJ UDWH DQG 1 1L DUH QRW JLYHQ KHUH 7KH 01f VWDWLVWLF SHUIRUPHG EHVW XQGHU H[SRQHQWLDO RU XQLIRUP FHQVRULQJ ZLWK 0/f FORVH EHKLQG 7DEOH FRQWDLQV UHVXOWV IURP WKH 1 1? DQG b FHQVRULQJ UDWH VLPXODWLRQ UXQV 7KH FHQVRUHG GDWD H[WHQVLRQ RI WKH QRUPDO VFRUHV VWDWLVWLF 16 LV LQFOXGHG VLQFH WKH XQGHUO\LQJ GLVWULEXWLRQ LV QRUPDO 1RWH KRZHYHU WKDW WKH /* VWDWLVWLF DOZD\V KDV JUHDWHU SRZHU LQ 7DEOH WKDQ WKH 16 VWDWLVWLF ZKLOH PDLQWDLQLQJ WKH QRPLQDO D 7KH 01f VWDWLVWLF DJDLQ DSSHDUV OLEHUDO XQGHU H[SRQHQWLDO FHQVRULQJ )RU WKRVH WHVWV PDLQWDLQLQJ VLJQLILFDQFH OHYHOV DW WKH QRPLQDO D f§ WKH 01f KDV WKH KLJKHVW SRZHU YDOXHV PRVW IUHTXHQWO\ ZLWK 0/f VHFRQG LQ IUHTXHQF\ RI KLJK SRZHU YDOXHV

PAGE 166

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ ZLWK b H[SRn QHQWLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI 1 1[ ([SRQHQWLDO DQG 8QLIRUP &HQVRULQJ 'LVWULEXWLRQV 7 f§ 7 7 7 $$$ 7HVW 6L]H /* f f f f f f f f f f 16 f f f f f f f f f f 01f f f f f f f f f f f 01f f f f f f f f f f f 0/f f f f f f f f f f f

PAGE 167

)RU WKH b FHQVRULQJ VLWXDWLRQ VLPLODU SDWWHUQV HPHUJHG IRU WKH -9 1L VDPSOH VL]HV 01f DQG 0/f ZHUH DPRQJ WKH VWDWLVWLFV ZLWK KLJK SRZHUV DQG DFFHSWDEOH VLJQLILFDQFH OHYHOV 7KH 0(9f DQG /* ZHUH WKH RWKHU VWDWLVWLFV ZLWK KLJK SRZHU $V ZLWK H[WUHPHYDOXH GLVWULEXWLRQ UHVXOWV WKH KLJKHU FHQVRULQJ UDWH UXOHG RXW PRUH RI WKH PL[HGPRGHO WHVWV RQ WKH EDVLV RI IDLOXUH WR PDLQWDLQ VLJQLILFDQFH OHYHOV (YHQ PRUH ZHUH UXOHG RXW ZKHQ WKH 1R 1L VLPXODWLRQV ZHUH UXQ LQFOXGLQJ /* 01f 0/f DQG 0(9f 2I WKH UHPDLQLQJ WHVWV ZLWK VLJQLILFDQFH OHYHOV ZLWKLQ WZR VWDQGDUG HUURUV RI XQGHU ERWK H[SRQHQWLDO DQG XQLIRUP FHQVRULQJ 0(9Of FRQVLVWHQWO\ KDG KLJKHU SRZHUV WKDQ WKH *+ 33 DQG 16 VWDWLVWLFV 5HVXOWV RI WKH b FHQVRULQJ UDWH ZLWK 1R 1L DUH FRQWDLQHG LQ 7DEOH $Q LQWHUHVWLQJ DVSHFW LV WKH SUHVHQFH RI ORZ EXW DFFHSWDEOH VLJQLILFDQFH OHYHOV XQGHU H[SRQHQWLDO FHQVRULQJ 7KH VWDWLVWLFV 01f 0/f DQG 0(9f DUH SUHIHUDEOH XQGHU H[SRQHQWLDO FHQVRULQJ ZKLOH WKH FKRLFH RI $ RU LQ 0/ f DQG 0(9 f PDNHV OLWWOH GLIIHUHQFH XQGHU XQLIRUP FHQVRULQJ 7KH /* VWDWLVWLF SHUIRUPV ZHOO UHODWLYH WR WKH PL[HGPRGHO WHVWV SDUWLFXODUO\ XQGHU XQLIRUP FHQVRULQJ )LQDOO\ ZKHQ WKH XQGHUO\LQJ VXUYLYDO ZDV &DXFK\ WKH VLJQLILFDQFH OHYHOV IRU DOO WKH WHVWV ZHUH TXLWH KLJK H[FHSW IRU WKH *+ 33 DQG 0& f VWDWLVWLFV LQ OLPLWHG LQVWDQFHV ZKHUH SRZHU WHQGHG WR EH YHU\ ORZ DV ZHOO ,QDGHTXDWH VDPSOH VL]H LV D SRVVLEOH UHDVRQ 5HVXOWV DUH QRW GLVSOD\HG KHUH ,Q VXPPDWLRQ WKH PL[HGPRGHO WHVWV EDVHG RQ 01f 0/f DQG 0(9f DUH UHFRPPHQGHG IRU XVH RQ VPDOO WR PRGHUDWHO\ FHQVRUHG GDWD ZKHQ WKH QRQUHVSRQGHUV

PAGE 168

7DEOH (PSLULFDO SRZHUV XQGHU D PL[HG QRUPDO GLVWULEXWLRQ DQG b H[SRQHQn WLDO DQG XQLIRUP LQ SDUHQWKHVHVf FHQVRULQJ UDWHV ZLWK JURXS VDPSOH VL]HV RI 1 1L ([SRQHQWLDO DQG 8QLIRUP &HQVRULQJ 'LVWULEXWLRQV 7 7 &7 2 ,, 1 ,, k &2 $ $ $ 7HVW 6L]H /*  01f f f f f f f f f f f 01f 0/f f f f f f f f f f f 0/f 0(9Of f 722 f f f f f f f f f 0(9f f f f f f f f f f f

PAGE 169

PRGHO DW f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n VHUYDWLRQV 7KH WHVW VWDWLVWLFV WKDW DUH DSSOLHG LQFOXGH WKH ORJUDQN /*f 01f 0(9f DQG 0/f $OVR LQFOXGHG LV WKH 3HWR3HWR JHQHUDOL]HG :LOFR[RQ 33f DV DQ LOOXVWUDWLRQ RI LWV SRRU SHUIRUPDQFH IRU QRQUHVSRQGHUV GDWD JRYHUQHG E\ WKH PL[WXUH PRGHO f 8QFHQVRUHG 'DWD ([DPSOH 7KH GDWD LQ 7DEOH DUH WDNHQ IURP &RQRYHU DQG 6DOVEXUJ 7DEOH f 7KH FKDQJH LQ SDLQ RQ VRPH DQDORJ VFDOH LV PHDVXUHG EHIRUH DQG DIWHU IRXU ZHHNV LQ WKLV DFXWH SDLQIXO GLDEHWLF QHXURSDWK\ VWXG\ 7KH YDOXHV LQ 7DEOH DUH DFWXDOO\ EDVHOLQH PHDVXUH? ? ILQDO PHDVXUH f f ZKHUH ILQDO PHDVXUH UHIHUV WR WKH UHFRUGHG SDLQ YDOXH DIWHU IRXU ZHHNV 7KH FRQWURO VXEMHFWV UHFHLYHG D SODFHER

PAGE 170

7DEOH &KDQJH LQ SDLQ PHDVXUHV IURP GLDEHWLF QHXURSDWK\ VWXG\ &RQWURO 6XEMHFWV 1R f 7UHDWPHQW 6XEMHFWV $A f 6RXUFH &RQRYHU DQG 6DOVEXUJ 7DEOH f 9DOXHV UHSUHVHQW WKH ORJDULWKP RI WKH UDWLR RI EDVHOLQH WR ILQDO PHDVXUHPHQWV

PAGE 171

7DEOH &RPSDULVRQ RI WHVW VWDWLVWLF YDOXHV XQFHQVRUHG GDWD H[DPSOH 7HVW 6WDWLVWLF 25 2XUV 01f 0(9Of : &6 &RQRYHU6DOVEXUJ &RQRYHU DQG 6DOVEXUJ f FRPSDUHG UHVXOWV IURP WKH FDOFXODWLRQV RI WKH :LOFR[RQ UDQN VXP WHVW 6WXGHQWfV WWHVW *RRGfV f WHVW WKH TXDQWLOH WHVW RI -RKQVRQ HW DO f 01f DQG IRXU RWKHU WHVWV EDVHG RQ VFRUHV VL fV ff LQ WKHLU QRWDWLRQf GHULYHG LQ WKHLU SDSHU 7KH VFRUHV V DUH LGHQWLFDO WR RXU 0(9 f VFRUHV ZLWK $ ORJf VV 7KH WHVW SURFHGXUH RI &RQRYHU DQG 6DOVEXUJ f XVH D YDULDQFH HVWLPDWRU EDVHG RQ WKH VXP RI VTXDUHG GHYLDWLRQV IURP WKH DYHUDJH RI WKH 1 VFRUHV HJ 5DQGOHV DQG :ROIH f WR VWDQGDUGL]H Y DQG HPSOR\ D WGLVWULEXWLRQ ZLWK 1 f§ GHJUHHV RI IUHHGRP WR FRPSXWH WKH SYDOXH )RU VDPSOHV VL]HV OLNH WKRVH LQ WKLV H[DPSOH D WGLVWULEXWLRQ DSSUR[LPDWLRQ ZLOO EH YHU\ FORVH WR WKH VWDQGDUG QRUPDO GLVWULEXWLRQ 7DEOH OLVWV WKH WHVW VWDWLVWLFV YDOXHV ZH FRPSXWHG ZLWK WKH YDULDQFH HVWLPDWRU 9L f DV FRPSDUHG WR WKH &RQRYHU DQG 6DOVEXUJ f YHUVLRQV 1RWH WKDW WKH REVHUYHG YDOXHV RI WKH WHVW VWDWLVWLFV DUH VLPLODU LQ HDFK URZ

PAGE 172

7DEOH 7HVW VWDWLVWLF YDOXHV DQG FRPSXWHG SYDOXHV XQFHQVRUHG GDWD H[DPSOH $ 7HVW 6WDWLVWLF 01 f >@ f§ f§ 0/ f >@ >@ >@ 0(9 f >@ >@ >@ /* >@ >@ >@ : >@ >@ >@ 7KH SYDOXHV DUH LQ > @ )URP RXU VLPXODWLRQ UHVXOWV LQ 6HFWLRQ DSSURSULDWH WHVW VWDWLVWLFV WR FRPSXWH IRU WKLV W\SH RI GDWD ZRXOG EH 01f 0/f DQG 0(9f 7DEOH FRQWDLQV UHVXOWV IURP WKHVH ODVW WKUHH WHVW VWDWLVWLFV DV ZHOO DV WKH :LOFR[RQ ORJUDQN /*f DQG UHVXOWV IURP WKH PL[HGPRGHO VWDWLVWLFV ZLWK VFRUHV XVLQJ $ RU $ ORJf m 7KH FRUUHVSRQGLQJ SYDOXHV DUH JLYHQ LQ EUDFNHWV 7KH PL[HGPRGHO WHVWV ZLWK 0/ f RU 0(9 f LQ 7DEOH VKRZ D WUHQG RI ORZHU SYDOXHV DV $ JURZV ODUJHU 7KH YDOXHV IRU WKH ORJUDQN WHVW DUH FRQVWDQW RI FRXUVH VLQFH WKH WHVW VWDWLVWLF GRHV QRW GHSHQG RQ $ 5HFDOO WKDW IRU XQFHQVRUHG GDWD WKH ORJUDQN UHGXFHV WR WKH H[SRQHQWLDO VFRUHV WHVW RI 6DYDJH f 7KH SYDOXH RI IRU /* LV YHU\ FRPSDUDEOH WR WKRVH SYDOXHV RI RWKHU VWDWLVWLFV LQFOXGLQJ WKH WHVWV RI &RQRYHU DQG 6DOVEXUJ f ZKR GLG QRW LQFOXGH LW /*f RQ JURXQGV RI fORVLQJ SRZHUf ZKHQ $

PAGE 173

 WHQGV DZD\ IURP &RQRYHU DQG 6DOVEXUJ f LQVWHDG UHFRPPHQG DQ fLQYHUVH 6DYDJHf VFRUH GHQRWHG E\ V f 7KH WHVW VWDWLVWLF EDVHG RQ WKH WKHVH LQYHUVH 6DYDJH VFRUHV V f \LHOGHG DQ REVHUYHG WHVW VWDWLVWLF YDOXH RI ZLWK SYDOXH IURP WKH GDWD )LJXUH LV SORW RI WHVW VWDWLVWLF EHKDYLRU RYHU WKH UDQJH RI YDOXHV $ >@ 7KH 0/ f 0(9 f /* 99 DQG 01f VWDWLVWLFV DUH LQFOXGHG 2EVHUYH WKDW IRU ERWK WKH 0/ f DQG 0(9 f VWDWLVWLFV WKH ORZHVW SYDOXH RU HTXLYDOHQWO\ E\ SURSHUWLHV WKH KLJKHVW WHVW VWDWLVWLF YDOXHf RFFXUV DW $ &HQVRUHG 'DWD ([DPSOH 7KH 9HWHUDQfV $GPLQLVWUDWLRQ 9$f OXQJ FDQFHU FOLQLFDO WULDO 3UHQWLFH .DOEIOHLVFK DQG 3UHQWLFH f FRQVLVWHG RI PDOHV ZLWK LQRSHUDEOH OXQJ FDQFHU WKDW ZHUH UDQGRPL]HG WR HLWKHU WKH VWDQGDUG RU D WHVW FKHPRWKHUDS\ $QDO\VLV 3UHQWLFH .DOEIOHLVFK DQG 3UHQWLFH f RI WKLV GDWD KDV WDNHQ LQWR DFFRXQW VHYHUDO FRYDULDWHV EHOLHYHG WR KDYH SURJQRVWLF HIIHFWV RQ WKH UHVSRQVH RI LQWHUHVW WLPH WR GHDWK 1LQH REVHUYDWLRQV RI WKH UHVSRQVH ZHUH FHQVRUHG 7KH .DOEIOHLVFK t 3UHQWLFH f DQDO\VHV ILW VHYHUDO UHJUHVVLRQ PRGHOV ZLWK WKH FRYDULDWHV WR VWXG\ WUHDWPHQW GLIIHUHQFHV 2QH RI WKH FRYDULDWHV LQGLFDWHG ZKHWKHU D SDWLHQW LQ WKH WULDO KDG UHFHLYHG DQ\ SULRU WKHUDS\ 7KLV FRYDULDWH ZDV QRW IRXQG WR KDYH D VLJQLILFDQW HIIHFW 7KHUH ZDV DOVR QR HYLGHQFH RI VLJQLILFDQWO\ LPSURYHG VXUYLYDO WLPH IRU SDWLHQWV UHFHLYLQJ WKH WHVW WKHUDS\ LQVWHDG RI WKH VWDQGDUG WKHUDS\ $ FRPSOHWH OLVWLQJ RI WKH GDWD FDQ EH IRXQG LQ $SSHQGL[ RI .DOEIOHLVFK DQG 3UHQWLFH f $ VXEVHW RI WKH GDWD IURP SDWLHQWV WKDW UHFHLYHG WKH WHVW WKHUDS\ LV

PAGE 174

3YDOXH 'HOWD )LJXUH *UDSK RI WHVW VWDWLVWLF EHKDYLRU XQFHQVRUHG GDWD H[DPSOH

PAGE 175

GLVSOD\HG LQ 7DEOH 7KLV VXEVHW RI GDWD LV GLYLGHG LQWR WZR JURXSVFRQWURO IRU WKRVH SDWLHQWV QRW UHFHLYLQJ DQ\ SULRU WKHUDS\ DQG fWUHDWPHQWf IRU WKRVH SDWLHQWV UHFHLYLQJ SULRU WKHUDS\ 7KH H[LVWHQFH RI RWKHU FRYDULDWHV VXFK DV FDQFHU FHOO W\SH ZKLFK KDV EHHQ IRXQG WR EH D VLJQLILFDQW IDFWRU RQ VXUYLYDO WLPH LQ UHJUHVVLRQ PRGHOV PD\ EH UHVSRQVLEOH IRU RQO\ D VPDOO SURSRUWLRQ RI VXEMHFWV LQ WKH WUHDWPHQW JURXS UHVSRQGLQJ ZLWK EHWWHU VXUYLYDO WLPHV 7KHUH DUH RQO\ WKUHH FHQVRULQJ WLPHV DPRQJ 7DEOH 6XUYLYDO WLPHV LQ GD\V IURP 9HWHUDQfV $GPLQLVWUDWLRQ OXQJ FDQFHU WULDO SDWLHQWV UHFHLYLQJ WHVW WKHUDS\ &RQWURO 1R 3ULRU 7KHUDS\f 3DWLHQWV 1R f &2 r 7UHDWPHQW 3ULRU 7KHUDS\f 3DWLHQWV 1L f r 6RXUFH .DOEIOHLVFK DQG 3UHQWLFH $SSHQGL[ ,f &HQVRUHG WLPHV WKH 1 REVHUYDWLRQV \LHOGLQJ DQ DSSUR[LPDWHO\ b FHQVRULQJ UDWH 7KH WHVW VWDWLVWLF UHVXOWV DUH GLVSOD\HG LQ 7DEOH

PAGE 176

7DEOH 3YDOXHV IRU 9$ OXQJ FDQFHU FHQVRUHG GDWD H[DPSOH 7HVW 6WDWLVWLF 2QH6LGHG 3YDOXH 7ZR6LGHG 3YDOXH 01f 0/f 0(9f /* 33 1RQH RI WKH WHVWV LQ 7DEOH VWURQJO\ LQGLFDWH D WUHDWPHQW HIIHFW DOWKRXJK 01f SURYLGHV PDUJLQDO HYLGHQFH QHDU WKH VLJQLILFDQFH OHYHO IRU D RQHVLGHG WHVW DQG QHDU WKH OHYHO IRU D WZRVLGHG WHVW 1RWLFH WKDW DOO WKUHH RI WKH PL[HG PRGHO WHVW VWDWLVWLFV 01f 0/f DQG 0(9f RXWSHUIRUP WKH ORJUDQN WHVW VWDWLVWLF

PAGE 177

&+$37(5 6800$5< $1' &21&/86,216 7KH fQRQUHVSRQGHUVf SUREOHP DULVHV LQ WKH VWXG\ RI D WUHDWPHQW ZKHUH WKH VXEn MHFWV UHFHLYLQJ WKH WUHDWPHQW PD\ RU PD\ QRW EH DIIHFWHG ,I D SURSRUWLRQ RI WKH VXEMHFWV UHFHLYLQJ WUHDWPHQW DUH QRW DIIHFWHG WKHQ RXWFRPH GDWD IURP WKHVH QRQn UHVSRQGHUV IROORZ WKH VDPH GLVWULEXWLRQ DV FRQWURO VXEMHFWV WKDW GLG QRW UHFHLYH WKH WUHDWPHQW $ PHDVXUHG RXWFRPH IRU VXEMHFWV LQ WKH WUHDWPHQW JURXS LV JRYHUQHG E\ D PL[WXUH PRGHO GHVFULEHG LQ 6HFWLRQ DQG SUHVHQWHG DW f LQ WKLV PDQXVFULSW 7KH PL[WXUH PRGHO DW f KDV EHHQ HPSOR\HG SUHYLRXVO\ LQ WKH VWDWLVWLFDO OLWHUDWXUH IRU XQFHQVRUHG GDWD ,Q WKLV GLVVHUWDWLRQ WKH SRWHQWLDO RI D UDQGRP FHQn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f 7KH WHVW EDVHG RQ Y FDQ DOVR KDQGOH WKH VLWXDWLRQ RI VWRFKDVWLFDOO\ VPDOOHU YDOXHV LQ WKH WUHDWPHQW JURXS VHH 6HFWLRQ IRU GHWDLOV

PAGE 178

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f RYHU WKH ORFDWLRQPRGHO WHVWV VXFK DV WKH ORJUDQN RU D JHQHUDOL]HG :LOFR[RQ LV PRVW DSSDUHQW IRU ODUJHU YDOXHV RI $ DQG VPDOOHU YDOXHV RI 7 LQ WKH XQGHUO\LQJ GLVWULEXWLRQ IRU WKH WUHDWPHQW JURXS 7HVWV EDVHG RQ VFRUHV GHULYHG IURP WKH ORJLVWLF DQG H[WUHPHYDOXH GLVWULEXWLRQV ZLWK D FKRVHQ YDOXH RI $ FDOOHG 0/f DQG 0(9f UHVSHFWLYHO\ DORQJ ZLWK D WHVW EDVHG RQ VFRUHV IURP WKH QRUPDO GLVWULEXWLRQ ZLWK D FKRVHQ YDOXH RI $ L H 01f SHUIRUPHG FRQVLVWHQWO\ ZHOO RYHU D ZLGH UDQJH RI GDWD FRQILJXUDWLRQV 7KHVH FRQILJXUDWLRQV GHVFULEHG LQ 6HFWLRQ f ZHUH FRQVWUXFWHG IURP YDU\LQJ VDPSOH VL]HV FHQVRULQJ GLVWULEXWLRQV DQG FHQVRULQJ UDWHV DQG VXUYLYDO GLVWULEXWLRQV $V WKH FHQVRULQJ UDWH EHFRPHV KHDY\ bf WKH ORJUDQN WHVW SHUIRUPV DV ZHOO DV WKH UHFRPPHQGHG PL[HG PRGHO WHVWV 0/f 0(9f DQG 01f $SSOLFDWLRQV WR VWXGLHV ZLWK XQFHQVRUHG GDWD RU FHQVRUHG GDWD DIILUPHG WKDW WKH 0/f 0(9f DQG 01f WHVWV SURYLGH WKH EHVW UHVXOWV ZLWK WKH ORJUDQN D ZRUWK\ FRPSHWLWRU

PAGE 179

$OO WKH SUDFWLFDO DSSOLFDWLRQV LQ WKLV PDQXVFULSW UHOLHG RQ DV\PSWRWLF WKHRU\ IRU WKH GLVWULEXWLRQ RI Y )XUWKHU UHVHDUFK RQ H[DFW SURFHGXUHV PD\ SURYH LQWHUHVWLQJ DQG XVHIXO 7KH FDOFXODWLRQ RI H[SHFWHG VFRUHV DQG D SHUPXWDWLRQ GLVWULEXWLRQ IRU D JLYHQ VHW RI GDWD PD\ SURYLGH PRUH DSSURSULDWH UHVXOWV SDUWLFXODUO\ IRU VPDOOHU M9 M9L f VDPSOH VL]HV ,PSOHPHQWDWLRQ RI WKH IRUP IRU HYDOXDWLQJ H[SHFWHG VFRUHV WKDW LV JLYHQ LQ 6HFWLRQ DSSHDUV WR LQYROYH FRQVLGHUDEOH FRPSXWHU SURn JUDPPLQJ DW WKLV SRLQW

PAGE 180

5()(5(1&(6 $DOHQ f 1RQSDUDPHWULF LQIHUHQFH IRU D IDPLO\ RI FRXQWLQJ SURFHVVHV $QQDOV RI 6WDWLVWLFV $OWVKXOHU % f 7KHRU\ IRU WKH PHDVXUHPHQW RI FRPSHWLQJ ULVNV LQ DQLPDO H[SHULPHQWV 0DWKHPDWLFDO %LRVFLHQFHV $QGHUVHQ 3 %RUJDQ *LOO 5 K .HLGLQJ 1 f /LQHDU QRQSDUDPHWn ULF WHVWV IRU FRPSDULVRQ RI FRXQWLQJ SURFHVVHV ZLWK DSSOLFDWLRQV WR FHQVRUHG VXUYLYDO GDWD ZLWK GLVFXVVLRQf ,QWHUQDWLRQDO 6WDWLVWLFDO 5HYLHZ %HFNHU 5 $ &KDPEHUV 0 t :LONV $ 5 f 7KH 1HZ 6 /DQJXDJH 3Dn FLILF *URYH &DOLIRUQLD :DGVZRUWK t %URRNV&ROH %RRV ' t %URZQLH & f 7HVWLQJ IRU D WUHDWPHQW HIIHFW LQ WKH SUHVHQFH RI QRQUHVSRQGHUV %LRPHWULFV &DUDQR $ t 0RRUH f 7KH UDWLRQDOH DQG PHWKRGRORJ\ IRU TXDQWLI\LQJ VLVn WHU FKURPDWLG H[FKDQJHV LQ KXPDQV ,Q 0XWDJHQLFLW\ 1HZ +RUL]RQV LQ *HQHWLF 7R[LFRORJ\ $ +HGGOH HGf 1HZ
PAGE 181

)LVKHU 5 $ t
PAGE 182

3HWR 5 t 3HWR f $V\PSWRWLFDOO\ HIILFLHQW LQYDULDQW UDQN WHVW SURFHGXUHV ZLWK GLVFXVVLRQf -RXUQDO RI WKH 5R\DO 6WDWLVWLFDO 6RFLHW\ $ 3UHQWLFH 5 / f ([SRQHQWLDO VXUYLYDOV ZLWK FHQVRULQJ DQG H[SODQDWRU\ YDULn DEOHV %LRPHWULND 3UHQWLFH 5 / f /LQHDU UDQN WHVWV ZLWK ULJKW FHQVRUHG GDWD %LRPHWULND 3UHQWLFH 5 / t 0DUHN 3 f $ TXDOLWDWLYH GLVFUHSDQF\ EHWZHHQ FHQVRUHG GDWD UDQN WHVWV %LRPHWULND 5DQGOHV 5 + t :ROIH $ f ,QWURGXFWLRQ WR WKH 7KHRU\ RI 1RQSDUDPHWULF 6WDWLVWLFV 1HZ
PAGE 183

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n PHQW +H KDV EHHQ D PHPEHU RI WKH $PHULFDQ 6WDWLVWLFDO $VVRFLDWLRQ VLQFH

PAGE 184

, FHUWLI\ WKDW KDYH UHDG WKLV VWXG\ DQG WKDW LQ P\ RSLQLRQ LW FRQIRUPV WR DFFHSWDEOH VWDQGDUGV RI VFKRODUO\ SUHVHQWDWLRQ DQG LV IXOO\ DGHTXDWH LQ VFRSH DQG TXDOLW\ DV D GLVVHUWDWLRQ IRU WKH GHJUHH RI 'RFWRU RI 3KLORVRSK\ 9n LOIR 3HMDYHU 9 5DR &KDLUPDQ 3URIHVVRU RI 6WDWLVWLFV FHUWLI\ WKDW KDYH UHDG WKLV VWXG\ DQG WKDW LQ P\ RSLQLRQ LW FRQIRUPV WR DFFHSWDEOH VWDQGDUGV RI VFKRODUO\ SUHVHQWDWLRQ DQG LV IXOO\ DGHTXDWH LQ VFRSH DQG TXDOLW\ DV D GLVVHUWDWLRQ IRU WKH GHJUHH RI 'RFWRU RI 3KLORVRSK\ 'HQQLV :DFNHUO\ &RFKDLL 3URIHVVRU RI 6WDWLVWLFV FHUWLI\ WKDW KDYH UHDG WKLV VWXG\ DQG WKDW LQ P\ RSLQLRQ LW FRQIRUPV WR DFFHSWDEOH VWDQGDUGV RI VFKRODUO\ SUHVHQWDWLRQ DQG LV IXOO\ DGHTXDWH LQ VFRSH DQG TXDOLW\ DV D GLVVHUWDWLRQ IRU WKH GHJUHH RI 'RFWRU RI 3KLORVRSK\ %RJDRV 6LYD]OLDQ 3URIHVVRU RI ,QGXVWULDO DQG 6\VWHPV (QJLQHHULQJ

PAGE 185

7KLV GLVVHUWDWLRQ ZDV VXEPLWWHG WR WKH *UDGXDWH )DFXOW\ RI WKH 'HSDUWPHQW RI 6WDWLVWLFV LQ WKH &ROOHJH RI /LEHUDO $UWV DQG 6FLHQFHV DQG WR WKH *UDGXDWH 6FKRRO DQG ZDV DFFHSWHG DV SDUWLDO IXOILOOPHQW RI WKH UHTXLUHPHQWV IRU WKH GHJUHH RI 'RFWRU RI 3KLORVRSK\ 'HFHPEHU 'HDQ *UDGXDWH 6FKRRO