A large number of papers have appeared in the last twenty years on estimating and predicting characteristics of finite populations. This monograph is designed to present this modern theory in a systematic and consistent manner. The authors' approach is that of superpopulation models in which values of the population elements are considered as random variables having joint distributions. Throughout, the emphasis is on the analysis of data rather than on the design of samples. Topics covered include: optimal predictors for various superpopulation models, Bayes, minimax, and maximum likelihood predictors, classical and Bayesian prediction intervals, model robustness, and models with measurement errors. Each chapter contains numerous examples, and exercises which extend and illustrate the themes in the text. As a result, this book will be ideal for all those research workers seeking an up-to-date and well-referenced introduction to the subject.

This book provides an updated account of the regression techniques employed in comparing analytical methods and to test the biases of one method relative to others - a problem commonly found in fields like analytical chemistry, biology, engineering, and medicine. Methods comparison involves a non-standard regression problem; when a method is to be tested in a laboratory, it may be used on samples of suitable reference material, but frequently it is used with other methods on a range of suitable materials whose concentration levels are not known precisely. By presenting a sound statistical background not found in other books for the type of problem addressed, this book complements and extends topics discussed in the current literature. It highlights the applications of the presented techniques with the support of computer routines implemented using the R language, with examples worked out step-by-step. This book is a valuable resource for applied statisticians, practitioners, laboratory scientists, geostatisticians, process engineers, geologists and graduate students.