This book provides an introduction to the bootstrap for readers who have professional interest in its methods but do not have a background in advanced mathematics. It offers reliable, authoritative coverage of the bootstrap's considerable advantages as well as its drawbacks.

Autorentext

Michael R. Chernick, PhD, is Principal Senior Statistician at United BioSource Corporation, providing statistical design and analysis for pharmaceutical research on a variety of diseases, including a recent emphasis on oncology. He has over twenty years of experience in the application of statistical methods to the pharmaceutical industry as well as to medical devices, energy data, engineering problems, and insurance data. His research interests include extreme value theory, outliers, data editing, time series, and bootstrap methods. Dr. Chernick is also the coauthor of Introductory Biostatistics for the Health Sciences (Wiley).

Klappentext

A practical and accessible introduction to the bootstrap method--newly revised and updated Over the past decade, the application of bootstrap methods to new areas of study has expanded, resulting in theoretical and applied advances across various fields. Bootstrap Methods, Second Edition is a highly approachable guide to the multidisciplinary, real-world uses of bootstrapping and is ideal for readers who have a professional interest in its methods, but are without an advanced background in mathematics.

Updated to reflect current techniques and the most up-to-date work on the topic, the Second Edition features:

• The addition of a second, extended bibliography devoted solely to publications from 1999-2007, which is a valuable collection of references on the latest research in the field

• A discussion of the new areas of applicability for bootstrap methods, including use in the pharmaceutical industry for estimating individual and population bioequivalence in clinical trials

• A revised chapter on when and why bootstrap fails and remedies for overcoming these drawbacks

• Added coverage on regression, censored data applications, P-value adjustment, ratio estimators, and missing data

• New examples and illustrations as well as extensive historical notes at the end of each chapter

With a strong focus on application, detailed explanations of methodology, and complete coverage of modern developments in the field, Bootstrap Methods, Second Edition is an indispensable reference for applied statisticians, engineers, scientists, clinicians, and other practitioners who regularly use statistical methods in research. It is also suitable as a supplementary text for courses in statistics and resampling methods at the upper-undergraduate and graduate levels.

Inhalt

Preface to Second Edition. Preface to First Edition.

Acknowledgments.

1. What Is Bootstrapping?

1.1. Background.

1.2. Introduction.

1.3. Wide Range of Applications.

1.4. Historical Notes.

1.5. Summary.

2. Estimation.

2.1. Estimating Bias.

2.2. Estimating Location and Dispersion.

2.3. Historical Notes.

3. Confi dence Sets and Hypothesis Testing.

3.1. Confi dence Sets.

3.2. Relationship Between Confi dence Intervals and Tests of Hypotheses.

3.3. Hypothesis Testing Problems.

3.4. An Application of Bootstrap Confi dence Intervals to Binary Dose-Response Modeling.

3.5. Historical Notes.

4. Regression Analysis.

4.1. Linear Models.

4.2. Nonlinear Models.

4.3. Nonparametric Models.

4.4. Historical Notes.

5. Forecasting and Time Series Analysis.

5.1. Methods of Forecasting.

5.2. Time Series Models.

5.3. When Does Bootstrapping Help with Prediction Intervals?

5.4. Model-Based Versus Block Resampling.

5.5. Explosive Autoregressive Processes.

5.6. Bootstrapping-Stationary Arma Models.

5.7. Frequency-Based Approaches.

5.8. Sieve Bootstrap.

5.9. Historical Notes.

6. Which Resampling Method Should You Use?

6.1. Related Methods.

6.2. Bootstrap Variants.

7. Effi cient and Effective Simulation.

7.1. How Many Replications?

7.2. Variance Reduction Methods.

7.3. When Can Monte Carlo Be Avoided?

7.4. Historical Notes.

8. Special Topics.

8.1. Spatial Data.

8.2. Subset Selection.

8.3. Determining the Number of Distributions in a Mixture Model.

8.4. Censored Data.

8.5. p-Value Adjustment.

8.6. Bioequivalence Applications.

8.7. Process Capability Indices.

8.8. Missing Data.

8.9. Point Processes.

8.10. Lattice Variables.

8.11. Historical Notes.

**9. When Bootstrapping Fails Along with Remedies for Failures.
**

9.1. Too Small of a Sample Size.

9.2. Distributions with Infi nite Moments.

9.3. Estimating Extreme Values.

9.4. Survey Sampling.

9.5. Data Sequences that Are M-Dependent.

9.6. Unstable Autoregressive Processes.

9.7. Long-Range Dependence.

9.8. Bootstrap Diagnostics.

9.9. Historical Notes.

Bibliography 1 (Prior to 1999).

Bibliography 2 (1999-2007).

Author Index.

Subject Index.