The Fallibility of Comparison Groups

Abstract

This article presents evidence strengthening the argument against comparison group strategies given the current state of knowledge. The comparison group for this study was drawn explicitly recognizing the self-selection issues. It drew youths from similar sources matched on attitudes related to California Conservation Corps (CCC) participation not usually measured and collected information explicitly designed to improve the statistical modeling of participation. Yet, as always, whether a comparison group strategy works is an empirical question. One believes the results from such a study only if they basically conform to one's prior beliefs, otherwise the suitability of a comparison group is suspect.

Get full access to this article

View all access options for this article.

References

Bloom, H. , L. Orr , G. Cave , S. Bell , and F. Doolittle. 1992. The national JTPA study: Title II impacts of earnings and employment at 18 months. Executive summary. Bethesda, MD: Abt Associates Inc.

Catsiapsis, G. , and C. Robinson. 1982. Sample selection bias with multiple selection rules: Application to student aid grants Journal of Econometrics 18:351-68.

Fraker, T. , and R. Maynard. 1987. Evaluating comparison group designs with employment-related programs Journal of Human Resources 22:194-227.

Friedlander, D. , and P.K. Robins. 1992. Estimating the effects of employment and training programs: An assessment of some nonexperimental techniques. New York: Manpower Development and Research Corporation.

Heckman, J. , V.J. Hotz , and M. Dabos. 1987. Do we need experimental data to evaluate the impact of manpower training on earnings Evaluation Review 11:395-427.

Lalonde, R. , and R. Maynard. 1987. How precise are evaluations of employment and training programs: Evidence from a field experiment Evaluation Review 11:428-51.