Simultaneous Inference in Regression

Wei Liu is a professor of statistics at the University of Southampton, UK. Dr. Liu has published more than 80 papers in peer-reviewed journals, including Annals of Statistics, Journal of the American Statistical Association, Journal of the Royal Statistical Society, Biometrika, and Biometrics. His research encompasses multiple comparison, simultaneous inference, and sequential methods.

I like in particular this book since almost all results are given with proofs and that these proofs are easy to understand having some knowledge in linear models. It is especially helpful that the geometric ideas behind the proofs are worked out and presented with many illustrations. Together with the comprehensive review of the published literature and the presentation of some unsolved problems, this book is very valuable for researchers. It is also very recommendable for practitioners since the ideas of the concepts are worked out clearly and many examples and figures are presented where the confidence bands are applied to real data. MATLAB programs for all methods can be downloaded from the author’s website.—Christine Müller, Biometrical Journal 53 (2011)This book provides a comprehensive discussion of methods for determining simultaneous confidence bands in regression. … The book provides a valuable up-to-date review of work in this area. —David J. Hand, International Statistical Review (2011), 79… definitely fills a significant niche, providing practitioners with powerful inference tools for parametric regression and stimulating further research in this important area.— Tatyana Krivobokova, Georg-August- Univer,citat Gottingen, Royal Statistics Society, February 2012

• Introduction to Linear Regression Analysis. Confidence Bands for One Simple Regression Model. Confidence Bands for One Multiple Regression Model. Assessing Part of a Regression Model. Comparison of Two Regression Models. Comparison of More Than Two Regression Models. Confidence Bands for Polynomial Regression. Confidence Bands for Logistic Regression. Appendices. Bibliography. Index.