Donald T. Campbell, PhD, before his death in 1996 was University Professor of Social Relations, Psychology, and Education at Lehigh University. He had previously taught at Ohio State University, the University of Chicago, Northwestern University, and Syracuse University. He was a member of the National Academy of Sciences and a President of the American Psychological Association. He was the recipient of 9 honorary doctorates.David A. Kenny, PhD, is Professor of Social Psychology at the University of Connecticut. He has been a visiting professor at Oxford University and Arizona State University, and was a Fellow at the Center for Advanced Study in the Behavioral Sciences.

"In a world that calls attention to extremes, both good and bad, it is critical that social scientists fully understand regression effects. Campbell and Kenny have produced a book on this topic that is destined to be a classic. Ideally suited for graduate students in the social sciences and for nonexperimental researchers, the book is comprehensive and accessible. These well known methodologists tell us how regression effects have fooled experts in psychology, education, and biology, and they explain clearly how the effects can be identified using graphical and statistical tools. Producers as well as critical consumers of empirical information will want this text on their shelves." --Patrick E. Shrout, PhD, Professor of Psychology, New York University"Elegant and concise....If you are a novice in the topic, you will become an expert by reading A Primer on Regression Artifacts. If you are already an expert, you will learn things you will be surprised you did not already know. In either case, you will find that the authors meet you more than halfway; they guide your inquiry with ample encouragement, engaging illustrations, and good humor....It is hard to imagine a duo that is more capable of making comprehensible a challenging methodological topic." --From the Foreword by Charles S. Reichardt, PhD, University of Denver"A Primer on Regression Artifacts is a valuable addition to the literature. The volume not only lays bare most of the secrets of regression toward the mean; it also explores correlation in general with great enthusiasm. In a most appropriate arena, this book further extends the vast legacy of the inimitable Donald T. Campbell. I will recommend it to advanced undergraduates, graduate students, and, most certainly, to my faculty colleagues in the behavioral and social sciences." --John R. Nesselroade, PhD, Hugh Scott Hamilton Professor of Psychology, University of Virginia"This important and useful volume brings together two of our greatest methodologists to tackle one of the thorniest methodological problems in the behavioral sciences. Using interesting examples from research and everyday life, Campbell and Kenny illustrate the diverse contexts in which regression to the mean can arise, and offer suggestions for minimizing its occurrence. Graduate students will find that the book's liberal use of new graphical illustrations makes this normally difficult material wonderfully accessible; established researchers will gain a new and deeper understanding of this classic problem in the study of change." --Stephen G. West, PhD, Department of Psychology, Arizona State University, Tempe, Arizona - All mental health researchers must read this book, which definitely explores a vital topic. It is a magnificent concluding collaboration between Kenny and the late Campbell, the 20th century's foremost behavioral science methodologist. --Readings, 12/13/2002

• 1. Graphical Introduction2. Mathematics and Special Cases3. Regression Artifacts Due to Extreme Group Selection4. Regression Artifacts Due to Matching 5. Regression Artifacts Due to Statistical Equating6. Regression Artifacts in Change Scores7. Regression Artifacts in Time-Series Studies8. Regression Artifacts in Longitudinal Studies9. Cross-Lagged Panel Correlation Analysis10. Conclusion* Glossary of Terms* Glossary of Symbols* Appendix A: Dice-Rolling Program and Data Sets Used as Illustrations* Appendix B: The Computation of Autocorrelations