Subset Selection in Regression - Miller, Alan

. .

Résumé :
Originally published in 1990, Subset Selection in Regression filled a gap in the literature, and its critical and popular success endured for more than a decade. The second edition continues that tradition and remains dedicated to the techniques for fitting and choosing models that are linear in their parameters and to understanding and correcting the bias introduced by selecting a model. The author thoroughly updated each chapter, added material that reflects recent developments in theory and methods, and included more examples and references. The presentation is clear, concise, and as the Journal of the American Statistical Association reported about the first edition, goes straight to the guts of a complex problem.

Sommaire:
Introduction. Least-Squares Computations. Finding Subsets which Fit Well. Hypothesis Testing. How Many Variables? Estimation after Model Selection. Bayesian Methods. Conclusions.