Regression modeling strategies. With applications to linear models, logistic regression, and survival analysis (Q495396)

This 2nd edition includes new chapters and sections, 225 new references mostly published 2001--2014, and incorporates comprehensive R software. In keeping with the previous edition (2001) [Zbl 0982.62063], this book is about the art and science of data analysis and predictive modeling. Major changes since the 1st edition include the following: (1) new text about problems with dichotomization of continuous variables and with classification; (2) addition of redundancy analysis; (3) a new section in Chapter 5 on bootstrap confidence intervals for ranking of predictors; (4) a new chapter on generalized least squares for analysis of serial response data; (5) a completely reworked case study in imputation and data reduction, with addition of sparse principal components; (6) new guidance on minimum sample sizes needed by some of the models; (7) de-emphasis of bootstrap bumping for obtaining simultaneous confidence regions, in favor of a multiplicity approach. The book is intended for Masters or Ph.D. level graduate students who had a general probability and statistics course and who are skilled in ordinary multiple regression and intermediate algebra. Examples used in the text mostly come from biomedical research, but the applied predictive models are useful in economics, sociology, psychology, engineering, and marketing as well.