This volume contains a collection of essays and discussions which serve as an introduction and guide to current research in the area of drawing inferences from self-selected samples. This topic is of direct interest to a professional audience of survey researchers, pollsters, market researchers, policymakers, statisticians, demographers, economists, and sociologists. The essays themselves and their associated critical discussions are clear and careful; the contributors are among the foremost experts in the field.
Contents: Preface. H. Wainer, Introduction and Overview. H. Wainer, The SAT as a Social Indicator: A Pretty Bad Idea. J. Hartigan, J.W. Tukey, Discussion 1: The SAT as a Social Indicator: A Pretty Bad Idea. B. Singer, Self-Selection and Performance-Based Ratings: A Case Study in Program Evaluation. J. Hartigan, J.W. Tukey, Discussion 2: Self-Selection and Performance-Based Ratings: A Case Study in Program Evaluation. J. Hartigan, J.W. Tukey, Discussion 3: Alternative Methods for Evaluating the Impact of Intervention. J.J. Heckman, R. Robb, Alternative Methods for Solving the Problem of Selection Bias in Evaluating the Impact of Treatments on Outcomes. J.W. Tukey, Comments. J.J. Heckman, R. Robb, Postscript: A Rejoinder to Tukey. R.J. Glynn, N.M. Laird, D.B. Rubin, Selection Modeling Versus Mixture Modeling With Nonignorable Nonresponse. J.W. Tukey, Discussion 4: Mixture Modeling Verus Selection Modeling With Nonignorable Nonresponse. P.W. Holland, A Comment on Remarks by Rubin and Hartigan.