Applied Regression Analysis for Business and Economics

Chapter 11, on robust regression, provides fairly thorough coverage of robust and resistant regression for an introductory book in regression analysis. Topics include M-estimation, least median of squares, least trimmed sum of squares, MM-estimators, (GM-estimators), compound (two-stage) estimators, R-estimators, L-estimators, and robust ridge estimation. There are numerous references to more detailed descriptions in other sources for the interested reader. Chapter 12 is a good introduction to nonlinear regression. Chapter 13 covers generalized linear models (GLMs). This chapter starts with binary logistic and Poisson regression models, then shows how they Ž t into the GLM framework. The chapter provides compact coverage of basic GLM terminology and an example using PROC GENMOD in SAS. Thumbnail sketches of autocorrelated errors, measurement errors in predictors, inverse regression (calibration), bootstrapping in regression, classiŽ cation and regression trees (CART, with the emphasis on regression), neural networks, and experimental design in regression are covered in Chapter 14. The interested reader will want to consult the references for more detailed treatments of these topics. The Ž nal chapter is a brief discussion of validating regression models. This chapter would probably Ž t better after Chapter 9, because it is an important topic and should be in the core set of chapters. Introduction to Linear Regression Analysis is particularly well suited as a text for an upper-level undergraduate or graduate-level course in regression analysis. The reader should have a basic knowledge of matrix algebra (which could be taught along the way in a course, with perhaps an introduction to matrix algebra at the beginning). A basic knowledge of mathematical statistics would also be helpful in deriving maximum beneŽ t from the book. Exercises at the ends of chapters provide a mix of applied and theoretical problems, leaning more toward the applied. Appendixes include statistical tables, lists of datasets used in the book, and supplemental technical material containing some matrix derivations not contained in the main text. Datasets from the book and extensive problem solutions are available from an ftp site. The instructor’s manual contains solutions to all exercises, electronic versions of all datasets, and questions and problems for use on examinations. The student solutions guide provides complete solutions to selected problems. References to a substantial number of books and journal articles in the regression literature are provided at the end of the book. I highly recommend the third edition of Introduction to Linear Regression Analysis to practitioners, students, and teachers of regression analysis.