Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control

formulas and tables for determining the sample sizes for inference on the ICC and kappa. The method, promoted appropriately, is based on precision of the desired estimate rather than hypothesis testing considerations. The final chapter comprises nine “workshops” containing datasets, SAS codes, and outputs illustrating the use of various formulas and techniques discussed in the preceding five chapters. The material covered is of current interest, the informal tone is pleasing to the reader, and the author provides several insightful comments. This book is suitable for a short course due to its expository nature. The reading could have been more enjoyable had not the text been marred by numerous typographical errors, many of which appear in the formulas. The flow was also hindered by frequent inconsistencies in notation. The errors are mostly minor, consisting mainly of jumbled up upperand lower-case letters and inconsistent use of “Kappa,” “kappa,” and the letter “k.” Also, Workshop 2 is introduced on page 10, before Workshop 1, which is featured on page 14. These irritants diminish the utility of the book. For readers of Technometrics, Measures of Interobserver Agreement would seem to be of limited usefulness. As for those applied statisticians engaged in biomedical research, it perhaps would be worthwhile to wait for the revised, corrected edition. At the moment, the coverage of this topic in the general references by Fleiss (1986) for the continuous data and Fleiss, Levin, and Paik (2003) for the nominal data appears adequate.