Regression modeling strategies. With applications to linear models, logistic regression and survival analysis (Q5940707)

This is a monograph on applied regression, which is composed of 20 chapters, an appendix and a large list of references. The book links standard regression modeling approaches with 1) methods for relaxing linearity assumptions that still allow one to easily obtain predictions and confidence limits and to do formal hypothesis tests; 2) nonadditive modeling approaches not requiring the assumption that interactions are always linear by linear; 3) methods for imputing missing data and for penalizing variance for incomplete data; 4) methods for handling large numbers of predictors; (5) data reduction methods; 6) methods for quantifying predictive accuracy of a fitted model; 7) powerful model validation techniques by the bootstrap, and 8) graphical methods for understanding complex models. The text is intended for Masters or Ph.D. level graduate students who have had a general introductory probability and statistics course and who are well versed in ordinary multiple regression and intermediate algebra. The book is also intended to serve as a reference for data analysis and statistical methodology.