Theory of preliminary test and Stein-type estimation with applications /
Saved in:
Author / Creator: | Saleh, A. K. Md. Ehsanes. |
---|---|
Imprint: | Hoboken, N.J. : Wiley ; Chichester : John Wiley [distributor], c2006. |
Description: | xxiii, 622 p. : charts ; 24 cm. |
Language: | English |
Subject: | |
Format: | Print Book |
URL for this record: | http://pi.lib.uchicago.edu/1001/cat/bib/5933025 |
Table of Contents:
- List of Figures
- List of Tables
- Preface
- 1. Introduction
- 1.1. Objective of This Book
- 1.2. Statistical Decision Principle
- 1.3. Quadratic Loss Function
- 1.4. Some Statistical Models with Preliminaries
- 1.4.1. Mean and Simple Linear Models
- 1.4.2. One-Sample Multivariate Model
- 1.4.3. ANOVA Models
- 1.4.4. Parallelism Models
- 1.4.5. Multiple Regression Model and General Linear Hypothesis
- 1.4.6. Simple Multivariate Linear Model
- 1.4.7. Discrete Data Models
- 1.5. Organization of the Book
- 1.6. Conclusions
- 1.7. Problems
- 2. Preliminaries
- 2.1. Normal Distribution
- 2.2. Chi-square Distribution and Properties
- 2.3. Some Results from Multivariate Normal Theory
- 2.4. Beta Distribution and Applications
- 2.5. Discrete Distributions
- 2.5.1. Binomial Distribution
- 2.5.2. Multinomial Distribution
- 2.6. Matrix Results
- 2.7. Large Sample Theory
- 2.7.1. Four Types of Convergence
- 2.7.2. Law of Large Numbers
- 2.7.3. Central Limit Theorems
- 2.8. Nonparametric Theory: Preliminaries
- 2.8.1. Order-Statistics, Ranks, and Sign Statistics
- 2.8.2. Linear rank-statistics (LRS)
- 2.8.3. Rank Estimators of the Parameters of Various Models
- 2.9. Problems
- 3. Preliminary Test Estimation
- 3.1. Simple Linear Model, Estimators, and Tests
- 3.1.1. Simple Linear Model
- 3.1.2. Estimation of the Intercept and Slope Parameter
- 3.1.3. Test for the Slope Parameter
- 3.2. PTE of the Intercept Parameter
- 3.2.1. UE, RE and PTE of the Intercept Parameter
- 3.2.2. Bias and MSE Expressions
- 3.2.3. Comparison of bias and mse functions
- 3.2.4. Optimum Level of Significance of Preliminary Test
- 3.3. Two-Sample Problem and Pooling of Means
- 3.3.1. Model
- 3.3.2. Estimation and Test of the Difference between Two Means
- 3.3.3. Bias and mse Expression of the Three Estimators of a Mean
- 3.4. One-Sample Problem: Estimation of Mean
- 3.4.1. Model
- 3.4.2. Unrestricted, Restricted, and Preliminary Test Estimators
- 3.4.3. Bias, mse, and Analysis of Efficiency
- 3.5. An Alternative Approach
- 3.5.1. Introduction
- 3.5.2. One-Sample Problem
- 3.5.3. Comparison of PTE, [theta superscript PT subscript n] and SE [theta superscript S subscript n]
- 3.5.4. Simple Linear Model and Shrinkage Estimation
- 3.5.5. The Two-Sample Problem and Shrinkage Estimation
- 3.6. Estimation with Nonnormal Errors
- 3.6.1. Unrestricted, Restricted, Preliminary Test and Shrinkage Estimators, and the Test of Slope
- 3.6.2. Conditions for Asymptotic Normality of the Unrestricted Estimators of Intercept and Slope Parameters
- 3.6.3. Asymptotic Distributional Bias and Mean Square Error Expressions, and Efficiency Analysis
- 3.7. Two-Sample Problem and Estimation of Mean
- 3.8. One-Sample Problem and Estimation of the Mean
- 3.9. Stein Estimation of Variance: One-Sample Problem
- 3.10. Nonparametric Methods: R-Estimation
- 3.10.1. Model and Assumptions
- 3.10.2. Test of Hypothesis
- 3.10.3. Estimation of Intercept and Slope Parameters
- 3.10.4. Asymptotic Distribution of Various Estimators and Their ADB and ADMSE Expressions
- 3.11. Conclusions
- 3.12. Problems
- 4. Stein-Type Estimation
- 4.1. Statistical Model, Estimation, and Tests
- 4.2. Preliminary Test Estimation
- 4.3. Stein-Type Estimators
- 4.3.1. Introduction
- 4.3.2. James-Stein Estimator (JSE)
- 4.3.3. Positive-Rule Stein Estimator (PRSE)
- 4.3.4. Sclove-Morris-Radhakrishnan Modifications
- 4.4. Derivation of the Stein-Type Estimators
- 4.4.1. Risk Difference Representation Approach
- 4.4.2. Empirical Bayes Estimation (EBE) Approach
- 4.4.3. Quasi-empirical Bayes or Preliminary Test Estimation Approach
- 4.4.4. How Close is the JS Estimator to the Bayes Estimator?
- 4.5. Stein-Type Estimation When the Variance is Unknown
- 4.5.1. Introduction: Model, Estimators, and Tests
- 4.5.2. Preliminary Test and Stein-Type Estimators
- 4.5.3. Empirical Bayes Estimation When the Variance Is Unknown
- 4.5.4. Bias, MSE Matrices, and Risk Expressions
- 4.5.5. Risk Analysis of the Estimators
- 4.5.6. An Alternative Improved Estimator of [theta]
- 4.6. Stein-Type Estimation: Nonnormal Distributions
- 4.6.1. Model, Estimation, and Test
- 4.6.2. Preliminary Test (or Quasi-empirical Bayes) Approach to Stein-Type Estimation of the Mean Vector
- 4.6.3. Asymptotic Distributional Bias Vector, Quadratic Bias, MSE Matrix, and Risk Expressions of the Estimators
- 4.7. Improving James-Stein Estimator Toward Admissible Estimator
- 4.7.1. Introduction
- 4.7.2. Improving [theta superscript S subscript n] via PTE
- 4.7.3. Iterative PTE to Obtain an Admissible Estimator
- 4.7.4. Extension to the Case Where the Variance Is Unknown
- 4.8. Confidence Set Estimation Based on Stein-Type Estimators
- 4.8.1. Introduction
- 4.8.2. Properties of the Recentered Confidence Set Based on PRSE
- 4.8.3. Confidence Set Based on Preliminary Test Estimator
- 4.8.4. Asymptotic Theory of Recentered Confidence Sets and Domination of Positive-Rule Coverage Probability
- 4.9. Nonparametric Methods: R-Estimation
- 4.9.1. Model and Assumption
- 4.9.2. Test of Hypothesis
- 4.9.3. Estimation of the Location Parameter
- 4.9.4. ADB, ADQB, ADMSE, and ADQR of the Estimators of Location Parameters
- 4.9.5. Asymptotic Properties of Confidence Sets
- 4.10. Conclusions
- 4.11. Problems
- 5. Anova Model
- 5.1. Model, Estimation, and Tests
- 5.1.1. ANOVA model
- 5.1.2. Estimation of the Parameters of the One-Way ANOVA Model
- 5.1.3. Test of Equality of the Treatment Means
- 5.2. Preliminary Test Approach and Stein-Type Estimators
- 5.2.1. Preliminary Test Approach (or Quasi-empirical Bayes Approach)
- 5.2.2. Bayes and Empirical Bayes Estimators of Treatment Means
- 5.3. Bias, Quadratic Bias, MSE, and Risk Expressions
- 5.3.1. Bias Expressions
- 5.3.2. MSE Matrix and Risk Expressions
- 5.4. Risk Analysis and Risk Efficiency
- 5.4.1. Comparison of [theta subscript n] and [theta subscript n]
- 5.4.2. Comparison of [theta superscript PT subscript n] and [theta subscript n] ([theta subscript n])
- 5.4.3. Comparison of [theta superscript S subscript n], [theta superscript S+ subscript n], and [theta subscript n]
- 5.5. MSE Matrix Analysis and Efficiency
- 5.5.1. Comparison of [theta subscript n] and [theta subscript n]
- 5.5.2. Comparison of [theta superscript PT subscript n] Relative to [theta subscript n] and [theta subscript n]
- 5.5.3. Comparison of [theta subscript n] and [theta superscript S subscript n] ([theta superscript S subscript n] and [theta superscript S+ subscript n])
- 5.6. Improving the PTE
- 5.7. ANOVA Model: Nonnormal Errors
- 5.7.1. Estimation and Test of Hypothesis
- 5.7.2. Preliminary Test and Stein-Type Estimators
- 5.8. ADB, ADQB, ADMSE, and ADQR of the Estimators
- 5.8.1. Asymptotic Distribution of the Estimators under Fixed Alternatives
- 5.8.2. Asymptotic Distribution of the Estimators under Local Alternatives
- 5.8.3. ADB, ADQB, MSE-Matrices, and ADQR of [theta superscript PT subscript n] [theta superscript S subscript n] and [theta superscript S+ subscript n]
- 5.9. Confidence Set Estimation
- 5.9.1. Confidence Sets and Coverage Probabilities
- 5.9.2. Analysis of the Confidence Sets
- 5.10. Asymptotic Theory of Confidence Set Estimation
- 5.10.1. Asymptotic Representations of Normalized Estimators under Fixed Alternatives
- 5.10.2. Asymptotic Coverage Probability of the Confidence Sets under Local Alternatives
- 5.11. Nonparametric Methods: R-Estimation
- 5.11.1. Model, Assumptions, and Linear Rank Statistics (LRS)
- 5.11.2. Preliminary Test and Stein-Type Estimators
- 5.11.3. Asymptotic Distributional Properties of R-Estimators
- 5.11.4. ADB, ADQB, ADMSE, and ADQR
- 5.12. Conclusions
- 5.13. Problems
- 6. Parallelism Model
- 6.1. Model, Estimation, and Test of Hypothesis
- 6.1.1. Parallelism Model
- 6.1.2. Estimation of the Intercept and Slope Parameters
- 6.1.3. Test of Parallelism
- 6.2. Preliminary Test and Stein-Type Estimators
- 6.2.1. The Estimators of Intercepts and Slopes
- 6.2.2. Bayes and Empirical Bayes Estimators of Intercepts and Slopes
- 6.3. Bias, Quadratic Bias, MSE Matrices, and Risk Expressions
- 6.3.1. Unrestricted Estimators of [beta] and [theta]
- 6.3.2. Restricted Estimators of [beta] and [theta]
- 6.3.3. Preliminary Test Estimators of [beta] and [theta]
- 6.3.4. James-Stein-type Estimators of [beta] and [theta]
- 6.3.5. Positive-Rule Stein Estimators of [beta] and [theta]
- 6.4. Comparison of the Estimators of the Intercept Parameter
- 6.4.1. Bias Comparison of the Estimators of the Intercept Parameter
- 6.4.2. MSE-matrix Comparisons
- 6.4.3. Weighted Risk Comparisons of the Estimators
- 6.5. Estimation of the Regression Parameters: Nonnormal Errors
- 6.5.1. Unrestricted, Restricted, Preliminary Test, James-Stein and Positive-Rule Stein Estimators and Test of Hypothesis
- 6.5.2. Conditions for Asymptotic Properties of the Estimators and Their Distributions
- 6.5.3. Asymptotic Distributions of the Estimators
- 6.5.4. Expressions for ADB, ADQB, ADMSE, and ADQR of the Estimators
- 6.6. Asymptotic Distributional Risk Properties
- 6.6.1. Comparison of [theta subscript n] and [theta subscript n]
- 6.6.2. Comparison of [theta superscript PT subscript n] and [theta subscript n]([theta subscript n])
- 6.6.3. Comparison of [theta superscript S subscript n] and [theta subscript n]([theta subscript n])
- 6.6.4. Comparison of [theta superscript S subscript n] and [theta superscript PT subscript n]
- 6.6.5. Comparison of [theta superscript S+ subscript n] and [theta superscript S subscript n], [theta subscript n], [theta superscript PT subscript n]
- 6.7. Asymptotic Distributional MSE-matrix Properties
- 6.8. Confidence Set Estimation: Normal Case
- 6.8.1. Confidence Sets for the Slope Parameters
- 6.8.2. Analysis of Coverage Probabilities
- 6.8.3. Confidence Sets for the Intercept Parameters when [sigma superscript 2] is Known
- 6.9. Confidence Set Estimation: Nonnormal Case
- 6.10. Nonparametric Methods: R-Estimation
- 6.10.1. Model, Assumptions, and Linear Rank Statistics
- 6.10.2. R-Estimation and Test of Hypothesis
- 6.10.3. Estimation of the Intercepts [theta subscript alpha] and the Slope [beta subscript alpha]
- 6.10.4. Asymptotic Distribution of the R-Estimators of the Slope Vector
- 6.10.5. Asymptotic Distributional Properties of the R-Estimators of Intercepts
- 6.10.6. Confidence Sets for Intercept and Slope Parameters
- 6.11. Conclusions
- 6.12. Problems
- 7. Multiple Regression Model
- 7.1. Model, Estimation, and Tests
- 7.1.1. Estimation of Regression Parameters of the Model
- 7.1.2. Test of the Null Hypothesis, H[beta] = h
- 7.2. Preliminary Test and Stein-Type Estimation
- 7.2.1. Preliminary Test (or Quasi-empirical Bayes) Approach
- 7.2.2. Bayes and Empirical Bayes Estimators of the Regression Parameters
- 7.3. Bias, Quadratic Bias, MSE, and Quadratic Risks
- 7.3.1. Bias Expressions
- 7.3.2. MSE Matrices and Weighted Risks of the Estimators
- 7.4. Risk Analysis of the Estimators
- 7.5. MSE-Matrix Analysis of the Estimators
- 7.6. Improving the PTE
- 7.7. Multiple Regression Model: Nonnormal Errors
- 7.7.1. Introduction
- 7.7.2. Estimation of Regression Parameters and Test of the Hypothesis
- 7.7.3. Preliminary Test and Stein-Type Estimation
- 7.8. Asymptotic Distribution of the Estimators
- 7.8.1. Asymptotic Distribution of the Estimators under Fixed Alternatives
- 7.8.2. Asymptotic Distribution of the Estimators under Local Alternatives, and ADB, ADQB, ADMSE, and ADQR
- 7.8.3. ADQR Analysis
- 7.9. Confidence Set Estimation
- 7.9.1. Preliminaries
- 7.9.2. Confidence Sets and the Coverage Probabilities
- 7.9.3. Analysis of the Coverage Probabilities
- 7.10. Asymptotic Theory of Confidence Sets
- 7.10.1. Confidence Sets
- 7.10.2. Asymptotic Properties of Confidence Sets
- 7.11. Nonparametric Methods: R-Estimation
- 7.11.1. Linear Rank Statistics, R-Estimators and Confidence Sets
- 7.11.2. Asymptotic Distributional Properties of the R-estimators
- 7.11.3. Asymptotic Properties of the Recentered Confidence Sets Based on R-Estimators
- 7.12. Conclusions
- 7.13. Problems
- 8. Regression Model: Stochastic Subspace
- 8.1. The Model, Estimation, and Test of Hypothesis
- 8.1.1. The Model Formulation
- 8.1.2. Mixed Model Estimation
- 8.1.3. Test of Hypothesis
- 8.1.4. Preliminary Test and Stein-type Mixed Estimators
- 8.2. Bias, MSE, and Risks
- 8.2.1. Bias and Quadratic Bias Expressions
- 8.2.2. MSE Matrix and Risk Expressions
- 8.2.3. MSE Matrix Comparisons of the Estimators
- 8.2.4. Risk Comparisons of the Estimations
- 8.3. Estimation with Prior Information
- 8.3.1. Estimation of [beta subscript 1] and Test of H[subscript 0 beta subscript 0] = H[subscript 1 beta subscript 1]
- 8.3.2. The Mixed Estimators
- 8.3.3. Bias Expressions
- 8.3.4. MSE Matrix and Risk Expressions
- 8.4. Stochastic Subspace Hypothesis: Nonnormal Errors
- 8.4.1. Introduction
- 8.4.2. Estimation of the Parameters and Test of Hypothesis
- 8.4.3. Preliminary Test and Stein-type Estimators
- 8.5. Asymptotic Distribution of the Estimators
- 8.5.1. Asymptotic Distribution of the Estimators under Fixed Alternatives
- 8.5.2. Asymptotic Distribution of the Estimators under Local Alternatives
- 8.6. Confidence Set Estimation: Stochastic Hypothesis
- 8.7. R-Estimation: Stochastic Hypothesis
- 8.8. Conclusions
- 8.9. Problems
- 9. Ridge Regression
- 9.1. Ridge Regression Estimators
- 9.1.1. Ridge Regression with Normal Errors
- 9.1.2. Nonparametric Ridge Regression Estimators
- 9.2. Ridge Regression as Bayesian Regression Estimators
- 9.3. Bias Expressions
- 9.3.1. Bias Vector of [beta superscript PT subscript n] (k)
- 9.4. Covariance, MSE Matrix, and Risk Functions
- 9.5. Performance of Estimators
- 9.6. Estimation of the Ridge Parameter
- 9.7. Conclusions
- 9.8. Problems
- 10. Regression Models with Autocorrelated Errors
- 10.1. Simple Linear Model with Autocorrelated Errors
- 10.1.1. Estimation of the Intercept and Slope Parameters when [rho] is Known
- 10.1.2. Preliminary Test and S-Estimation of [beta] and [theta]
- 10.1.3. Estimation of the Intercept and Slope Parameters When Autocorrelation Is Unknown
- 10.2. Multiple Regression Model with Autocorrelation
- 10.2.1. Estimation of [beta] and Test of Hypothesis of H[beta] = h
- 10.2.2. Preliminary Test, James-Stein and Positive-Rule Stein-Type Estimators of [beta]
- 10.3. Bias, MSE Matrices, and the Risk of Estimators When [rho] Is Known
- 10.4. ADB, ADMSE, and ADQR of the Estimators ([rho] Unknown)
- 10.5. Estimation of Regression Parameters When [rho] Is Near Zero
- 10.5.1. Preliminary Test and Stein-Type Estimators (Chen and Saleh, 1993)
- 10.5.2. Design of Monte Carlo Experiment
- 10.5.3. Empirical Results and Conclusions
- 10.6. Estimation of Parameters of an Autoregressive Gaussian Process
- 10.6.1. Estimation and Test of Hypothesis
- 10.6.2. Asymptotic Theory of the Estimators and the Test-Statistics
- 10.6.3. ADB, ADMSE Matrices, and ADQR of the Estimators
- 10.7. R-Estimation of the Parameters of the AR[p]-Models
- 10.7.1. R-Estimation of the Parameters of the AR[p] Model
- 10.7.2. Tests of Hypothesis and Improved R-Estimators of [theta]
- 10.7.3. Asymptotic Bias, MSE Matrix, and Risks of the R-Estimators
- 10.8. R-Estimation of the Parameters with AR[1] Errors
- 10.9. Conclusions
- 10.10. Problems
- 11. Multivariate Models
- 11.1. Point and Set Estimation of the Mean Vector of an MND
- 11.1.1. Model, Estimation, and Test of Hypothesis
- 11.1.2. Bias, QB, MSE Matrix, and Weighted Risk Expressions of the Estimators
- 11.1.3. Risk and MSE Analysis of the Estimators
- 11.2. U-statistics Approach to Estimation
- 11.2.1. Asymptotic Properties of Point and Set Estimation under Fixed Alternatives
- 11.2.2. Asymptotic Properties of the Point and Set Estimation under Local Alternatives
- 11.3. Nonparametric Methods: R-estimation
- 11.3.1. Asymptotic Properties of the Point Estimators
- 11.3.2. Asymptotic Properties Confidence Sets
- 11.4. Simple Multivariate Linear Regression Model
- 11.4.1. Model, Estimation and Tests
- 11.4.2. Preliminary Test and Stein-Type Estimators
- 11.4.3. Bias, Quadratic Bias, MSE Matrices, and Risk Expressions of the Estimators
- 11.4.4. Two-Sample Problem and Estimation of the Means
- 11.4.5. Confidence Sets for the Slope and Intercept Parameters
- 11.5. R-estimation and Confidence Sets for Simple Multivariate Model
- 11.5.1. Introduction
- 11.5.2. Asymptotic Properties of the R-estimators
- 11.6. Conclusions
- 11.7. Problems
- 12. Discrete Data Models
- 12.1. Product of Bernoulli Models
- 12.1.1. Model, Estimation, and Test
- 12.1.2. Bayes and Empirical Bayes Estimation
- 12.1.3. Asymptotic Theory of the Estimators and the Test of Departure
- 12.1.4. ADB, ADQB, ADMSE, and ADQR of Estimators
- 12.1.5. Analysis of the Properties of Estimators
- 12.1.6. Baseball Data Analysis
- 12.1.7. Asymptotic Properties of Confidence Sets
- 12.2. Product Binomial Distributions
- 12.2.1. Introduction
- 12.2.2. Model, Estimation, and Test of Hypothesis
- 12.2.3. Asymptotic Theory of the Estimators and the Test-Statistics
- 12.2.4. ADB, ADQB, ADMSE, and ADQR of the Estimators
- 12.2.5. Estimation of Odds Ratio under Uncertain Zero Partial Association
- 12.2.6. Odds Ratios: Application to Meta-analysis of Clinical Trials
- 12.3. Product of Multinomial Models
- 12.3.1. The Product of Multinomial Models
- 12.3.2. Estimation of the Parameters
- 12.3.3. Test of Independence in an r x c Contingency Table
- 12.3.4. Preliminary Test and Stein-Type Estimators of the Cell Probabilities
- 12.3.5. Bayes and Empirical Bayes Method
- 12.3.6. Asymptotic Properties
- 12.3.7. Asymptotic Properties of the Estimators under Local Alternatives
- 12.3.8. Analysis of the Asymptotic Properties of the Estimators
- 12.4. Conclusions
- 12.5. Problems
- References
- Glossary
- Authors Index
- Subject Index