This is a reference book for bootstrap methods intended for applied researchers and mathematical statisticians. The text consists of nine chapters covering estimation, confidence intervals, regression, time series, special topics, and an extensive bibliography (nearly 1/3 of the pages). This is not intended to be a course textbook, so there are no problems or exercises. Although one of the stated purposes of the book is to provide an introduction to bootstrap techniques, it is really more successful in describing applications of bootstrap methods. A strong point of this book is that it provides a historical perspective on the dramatic development of both the applications and the theory in the Historical Notes sections in each chapter. The introductory chapter describes the evolution of the author's own interest in bootstrap methodology and includes his experience in explaining the bootstrap to the engineering community. Applications in engineering and clinical medicine are introduced. The Historical Notes is the longest part of this chapter and is an interesting account of the development of the bootstrap. Chapter 2 presents bootstrap estimation in the context of bias estimation of error rates in classification (two-class discrimination). This context was clearly determined by the author's extensive knowledge of this problem and includes references to much of his own published research. Chapter 3 describes various types of bootstrap confidence intervals and includes an example based on a clinical trial. Chapter 4 presents bootstrap methods for regression and includes an engineering-based example of bootstrap standard error estimates for nonlinear model parameters. Chapter 5 presents bootstrap techniques for forecasting and time series and completes the description of bootstrap methods. The remaining chapters deal with more general bootstrap topics. Chapter 6 describes related methods (jackknife, delta method, cross-validation; and Bayesian, smoothed, parametric and double bootstrap techniques). Chapter 7 discusses choosing the number of bootstrap replications and variance reduction methods. Special topics in Chapter 8 include determining the number of components in a mixture and bootstrap confidence interval estimation of the Cpk process capability index with skewed data. The final chapter presents situations in which bootstrap techniques fail and describes a bootstrap diagnostic (jackknife-after-bootstrap). This is not a gentle introduction to the topic but was intended to supplement material from Efron and Tibshirani (1993). Although most of the text is presented at a basic technical level, there are more advanced theoretical sections. The bibliography is extensive and references cited in the text are identified. The associated text page numbers for cited references are not included in the bibliography, but there are author and subject indexes. I found several typographical errors that the author has indicated will be corrected in future printings. In summary, this book can serve as a useful resource when trying to locate research papers on bootstrap methods and specific applications and will enhance understanding of the historical development of this important area of modern statistics.