Originally published in 1990, Subset Selection in Regression filled a gap in the literature. Its critical and popular success has continued for more than a decade, and the second edition promises to continue that tradition. The author has thoroughly updated each chapter, added material that reflects developments in theory and methods, and included more examples and recent references. His treatment now includes a new chapter on Bayesian methods, greater emphasis on least-squares projections, and more material on cross-validation. The presentation is clear, concise, and as the Journal of the ASA reported about the first edition, goes "straight to the guts of a complex problem."