did-you-know? rent-now

Amazon no longer offers textbook rentals. We do!

did-you-know? rent-now

Amazon no longer offers textbook rentals. We do!

We're the #1 textbook rental company. Let us show you why.

9780471496700

Multivariate Permutation Tests With Applications in Biostatistics

by
  • ISBN13:

    9780471496700

  • ISBN10:

    0471496707

  • Edition: 1st
  • Format: Hardcover
  • Copyright: 2001-06-08
  • Publisher: WILEY
  • Purchase Benefits
  • Free Shipping Icon Free Shipping On Orders Over $35!
    Your order must be $35 or more to qualify for free economy shipping. Bulk sales, PO's, Marketplace items, eBooks and apparel do not qualify for this offer.
  • eCampus.com Logo Get Rewarded for Ordering Your Textbooks! Enroll Now
List Price: $229.27 Save up to $0.15
  • Buy New
    $229.12
    Add to Cart Free Shipping Icon Free Shipping

    PRINT ON DEMAND: 2-4 WEEKS. THIS ITEM CANNOT BE CANCELLED OR RETURNED.

Supplemental Materials

What is included with this book?

Summary

Complex multivariate problems are frequently encountered in many scientific disciplines and it can be very difficult to obtain meaningful results. Permutation and nonparametric combination methods provide flexible solutions to complex problems by reducing the problem down to a set of simpler sub-problems. The author presents a novel but well tested approach using real examples taken from biomedical research. Statistical analyses are performed in a nonparametric setting, so that no assumptions need be made about the underlying distribution and the dependence relations between variables. ? Provides a clear exposition of the use of multivariate permutation testing, with emphasis on the use of nonparametric combination methodology. ? Growing area of research with many practical applications, notably in biostatistics. ? Numerous case studies and examples help to illustrate the theory. ? Provides solutions to multi-aspect problems, to problems with missing data, analysis of factorial designs and repeated measures. ? Explains the analysis of categorical, ordered categorical, binary, continuous, and mixed variables in both an experimental and an observational context. ? NPC-Test? software (demo copy), SAS macros, S-Plus code and datasets are available on the Web at http://www.stat.unipd.it/~pesarin/ For researchers and practitioners in a number of scientific disciplines, particularly biostatistics, the vast collection of techniques, examples and case studies will be an invaluable resource. Graduate students of applied statistics and nonparametric methods will find the book provides an accessible introduction to multivariate permutation testing.

Author Biography

Fortunato Pesarin is with the Department of Statistics, University of Padova, Italy. Professor Pesarin has been actively involved in the areas of multidimensional testing and permutation for almost 40 years, and is the author of dozens of publications in numerous international journals.

Table of Contents

Preface xv
Notation and Abbreviations xxiii
Introduction
1(16)
On Permutation Analysis
1(2)
Conditionality and Exchangeability
3(3)
The Permutation Testing Principle
6(3)
Permutation Approaches
9(1)
Randomization and Permutation
10(1)
When Conditioning Is Appropriate
11(2)
Computational Aspects
13(2)
Basic Notation
15(2)
Discussion of a Simple Testing Problem
17(20)
A Problem with Paired Observations
17(5)
Introduction
17(1)
A Motivating Example
17(2)
Modelling Responses
19(1)
Symmetry Induced by Exchangeability
20(1)
Further General Aspects
21(1)
The Student t Paired Solution
22(1)
Paired Normal Data
22(1)
An Extension
23(1)
The Signed Rank Test Solution
23(1)
Paired Continuous Data
23(1)
Generalized Scores
24(1)
The McNemar Solution
24(2)
Test on Signs of Differences
24(2)
An Extension
26(1)
The Permutation Solution
26(2)
General Aspects
26(1)
The Permutation Sample Space
27(1)
The Conditional Monte Carlo Method
28(3)
A Simulation Algorithm for Inspecting Permutation Sample Spaces
28(1)
A Routine for Random Permutations
29(1)
Approximating the Permutation Distribution
30(1)
Permutation Confidence Interval for δ
31(3)
Introductory Aspects
31(1)
An Approximate Solution
32(1)
A Conditional Monte Carlo Algorithm
33(1)
Problems and Exercises
34(3)
Theory of Permutation Tests for One-Sample Problems
37(36)
Introduction
37(6)
Basic Concepts
37(4)
On Sufficient Statistics for Symmetric Data
41(2)
Equivalence of Permutation Statistics
43(1)
Formal Definition of Permutation Tests
44(4)
Randomized Permutation Tests
44(2)
Non-randomized Permutation Tests
46(2)
Arguments Related to Permutation Tests
48(4)
General Aspects
48(1)
Arguments for Selecting a Test Statistic T
49(3)
Examples of One-Sample Problems
52(3)
Other Properties of Permutation Tests
55(12)
Stochastic Ordering of p-values
55(2)
Conditional and Unconditional Properties
57(2)
Further Unconditional Properties
59(1)
Some Consequences of the Theorems
60(3)
Comments on Power Functions
63(1)
An Algorithm for Evaluating the Conditional Power
64(2)
Permutation Testing for Composite Hypotheses
66(1)
Optimal Properties
67(2)
Introductory Remarks
67(1)
Further Remarks
68(1)
Problems and Exercises
69(4)
Examples of Univariate Multi-Sample Problems
73(28)
Introduction
73(2)
General Aspects
73(1)
On Permutation Distributions
73(2)
Inspection of the Permutation Sample Space
75(9)
Conditional Monte Carlo Method
75(1)
An Example
76(5)
Rank Solutions
81(1)
A Simple routine for Random Permutations
81(1)
Permutation Confidence Interval for δ
82(1)
Problems and Exercises
83(1)
Permutation One-Way ANOVA
84(5)
An Example
84(1)
Modelling Responses
85(1)
Permutation Solutions
86(2)
Problems and Exercises
88(1)
Goodness-of-Fit for Ordered Categorical Variables
89(7)
Introduction
89(1)
Goodness-of-Fit Tests for Ordered Categorical Variables
90(1)
A Solution Based on Score Transformations
91(1)
Typical Goodness-of-Fit Solutions
92(1)
Extension to Non-dominance Alternatives and C Groups
93(2)
Problems and Exercises
95(1)
A Problem with Repeated Observations
96(5)
Introduction
96(1)
Friedman's Rank Test
97(1)
A Permutation Solution
98(1)
An Example
99(1)
Problems and Exercises
99(2)
Theory of Permutation Tests for Multi-Sample Problems
101(32)
Introduction
101(1)
Recalling Basic Notions
101(1)
Recalling the Non-randomized Version
102(1)
Examples of Multi-Sample Problems
102(9)
Unbiasedness and Power of Some Multi-Sample Tests
111(10)
Unbiasedness and Power for Two-Sample Location Problems
111(5)
Some Corollaries
116(2)
Unbiasedness of One-Way ANOVA
118(3)
Some Asymptotic Properties
121(2)
Introduction
121(1)
Two Basic Theorems
121(2)
Permutation Central Limit Theorems
123(4)
Basic Notions
123(1)
Permutation Central Limit Theorems
124(3)
Problems and Exercises
127(6)
Nonparametric Combination Methodology
133(48)
Introduction
133(7)
General Aspects
133(2)
Bibliographic Notes
135(1)
Main Assumptions and Notation
136(3)
Some Comments
139(1)
The Nonparametric Combination Methodology
140(25)
Assumptions on Partial Tests
140(1)
Desirable Properties of Combining Functions
141(2)
A Two-Phase Algorithm for Nonparametric Combination
143(4)
Some Useful Combining Functions
147(8)
Four Examples of Nonparametric Combination
155(8)
Problems and Exercises
163(2)
Consistency and Unbiasedness of Combined Tests
165(7)
Consistency
165(1)
Unbiasedness
166(2)
A Not Consistent Combining Function
168(2)
Problems and Exercises
170(2)
Some Further Asymptotic Properties
172(5)
General Conditions
172(1)
Further Asymptotic Properties
173(4)
Comments of Nonparametric Combination
177(4)
General Comments
177(2)
Final Remarks
179(2)
Examples of Nonparametric Combination
181(48)
Introduction
181(1)
Permutation Testing with Multivariate Paired Observations
182(11)
Formal Description of Testing Problems
182(4)
An Example
186(2)
A Multivariate Extension of McNemar's Test
188(3)
Asymptotic Behaviour of Multivariate Tests with Paired Observations
191(1)
Problems and Exercises
192(1)
Permutation MANOVA with Mixed Data
193(13)
A Formal Description
193(3)
An Example with Four Categorical Variables
196(2)
A Two-Sample Multivariate Test
198(3)
A Multivariate Extension of Fisher's Exact Probability Test
201(1)
A Cross-over Design
202(2)
Problems and Exercises
204(2)
Goodness-of-Fit Tests for Ordered Categorical Variables
206(7)
Revisiting the Problem
206(2)
Some Extensions
208(2)
Two Examples
210(1)
Some Power Evaluations
211(2)
A Problem of Isotonic Inference
213(6)
Introduction
213(1)
Conditions for Nonparametric Combination
214(2)
An Application from Genetics
216(1)
An Example
217(1)
A Multivariate Extension
217(2)
A Problem with Multivariate Homoscedastic Repeated Responses
219(5)
A Formal Description
219(3)
An Algorithm for Conditional Simulation
222(1)
An Example
222(1)
Problems and Exercises
223(1)
Power Behaviour and Remarks on Restricted Alternatives
224(5)
Power Behaviour of combined Tests
224(2)
Remarks on Restricted Alternatives
226(2)
A Few Simulation Results
228(1)
Permutation Analysis in Factorial Designs
229(50)
Introduction
229(3)
General Aspects
229(1)
Solutions Based on Residuals
230(2)
Exact Separate Tests for Replicated 22 Factorial Designs
232(5)
Separate Sets of Hypotheses
232(1)
Synchronized Permutations
233(4)
Exact Tests for 22 Unbalanced Designs
237(4)
Weighting Intermediate Statistics for Factor A
237(2)
Weighting Intermediate Statistics for Factors B and AB
239(1)
An Extension of Welch's Test for Heteroscedastic Models
239(2)
Exact Tests in I x J Balanced Designs
241(5)
Balanced Two-Way Layout
241(1)
Separate Testing
241(2)
Some Comments
243(1)
Multivariate Extension I x J Designs
243(1)
Extension to a Kind of Unbalanced Heteroscedastic Model
244(2)
Synchronized Tests in Replicated 2k Factorials
246(9)
Extension to 2k Factorial Designs
246(1)
Realignments
247(3)
Construction of Test Statistics
250(5)
General Characterization of Synchronized Tests
255(4)
Characterizing Synchronized Permutations
255(1)
Synchronized Permutation Tests for Fractional Designs of Different Resolution
256(3)
A Comparing Simulation Study
259(3)
Comparing Solutions in H0
259(2)
Power Results
261(1)
An Application
262(2)
Permutation Tests in Unreplicated Factorials
264(7)
Introduction
264(3)
Paired Permutation Tests
267(1)
Paired Permutation Testing Algorithm
268(1)
Paired Permutation Testing Algorithm
268(3)
Problems and Exercises
271(1)
Appendices
272(7)
Sufficient Statistics for Replicated 22 Factorial Designs
272(2)
A Brief Review of Two-Level Factorial Designs
274(5)
Permutation Testing with Missing Data
279(26)
Introduction
279(2)
General Aspects
279(1)
Bibliographic Notes
280(1)
On Missing Data Processes
281(1)
Introduction
281(1)
Data Missing completely at Random
281(1)
Data Missing Not at Random
282(1)
The Permutation Approach
282(3)
Introduction
282(2)
Breaking Down the Hypotheses
284(1)
The Structure of Testing Problems
285(3)
Hypotheses for Non-MAR Models
285(1)
Hypotheses for MCAR Models
286(1)
Permutation Structure with Missing Values
287(1)
Permutation Analysis of Missing Values
288(7)
Partitioning the Permutation Sample Space
288(2)
Solution for Two-Sample MCAR Problems
290(2)
Extensions to Multivariate C-sample Problems
292(1)
Extension to Non-MAR Models
293(1)
Some Comments
293(2)
An Example of a Non-MAR Model
295(4)
Introduction
295(1)
The Example
296(1)
The Permutation Solution
297(2)
An Example with Multivariate Paired Observations
299(2)
The Problem
299(1)
An Example with Fictitious Data
300(1)
Power Behaviour of Some Tests with Missing Values
301(2)
Introduction
301(1)
Simulation Results and Comments
302(1)
Problems and Exercises
303(2)
The Behrens-Fisher Permutation Problem
305(24)
Introduction
305(3)
General Aspects
305(1)
Bibliographic Notes
306(1)
Formal Description of the Problem
307(1)
Parametric Solutions
308(2)
Basic Statistics
308(1)
Known Covariance Matrices
309(1)
Unknown Proportional Covariance Matrices
309(1)
Unknown Covariance Matrices
309(1)
A First Approximate Permutation Solution
310(3)
Approximate Solution Based on Aspin and Welch Statistics
310(1)
An Example
311(1)
Extension of Approximate Solution to Multivariate Situations
312(1)
An Almost Exact Permutation Solution
313(4)
A Univariate Solution by Testing for Symmetry
313(2)
Combining Two Tests of Symmetry
315(1)
Asymptotic Behaviour
316(1)
Extension to C > 2 Groups
317(1)
Multivariate Permutation Solutions
318(3)
Multivariate Solutions for Symmetric Distributions
318(1)
Three Multivariate Testing Problems
319(2)
Distributional Behaviour
321(3)
A Simulation Study in H0
321(1)
A Simulation Study in H1
322(2)
Permutation Testing for Location and Scale Coefficients
324(2)
An Approximate Solution for Scale Coefficients
324(1)
Joint Permutation Testing for Location and Scale Coefficients
325(1)
Problems and Exercises
326(3)
Permutation Testing for Repeated Measurements
329(18)
Introduction
329(1)
Modelling Repeated Measurements
330(3)
A General Additive Model
330(2)
The Hypotheses of interest
332(1)
Testing Solutions
333(5)
Solutions by the Nonparametric Combination Approach
333(2)
Analysis of Two-Sample Dominance Problems
335(1)
An Example from the Literature
335(2)
Some Power Evaluations
337(1)
Testing for Repeated Measurements with Missing Data
338(5)
Introduction
338(1)
A Formal Description of the Problem
338(2)
An Example
340(1)
A Comparative Simulation Study
341(2)
Tests for Balanced and Unbalanced Repeated Measures Designs
343(2)
Repeated Measures on 22 Unbalanced Factorials
343(1)
On I X J Balanced Designs
344(1)
Problems and Exercises
345(2)
Further Applications
347(24)
Introduction
347(1)
Morphological Differences in Biting Files
348(2)
Description of the Problem
348(1)
Results of Analysis
349(1)
A Clinical Trial on a Respiratory Drug
350(2)
Description of the Problem
350(1)
Results of Analysis
351(1)
A Medical Experiment on Diabetic Patients
352(3)
Description of the Problem
352(1)
Results of Analysis
353(2)
A Case Study of Recovery Wards
355(3)
Description of the Problem
355(2)
Results of Analysis
357(1)
Analysis of Experimental Tumour Growth Curves
358(3)
Description of the Problem
358(2)
Results of Analysis
360(1)
An Epidemiological Survey
361(4)
Description of the Problem
361(2)
Results of Analysis
363(2)
Appendix: NPC Test 2.0 Software for Multivariate and Multivariate Permutation Analysis
365(6)
References 371(28)
Index 399

Supplemental Materials

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

Rewards Program