ACCOUNTING FOR DROPOUTS IN EVALUATIONS OF SOCIAL PROGRAMS

This paper explores issues that arise in the evaluation of social prog rams using experimental data in the frequently encountered case where some of the experimental treatment group members drop out of the progr am prior to receiving treatment. We begin with the standard estimator for this case and the identifying assumption upon which it rests. We t hen examine the behavior of the estimator when the dropouts receive a partial ''dose'' of the program treatment prior to dropping out of the program. In the case of partial treatment, the identifying assumption is typically violated, thereby making the estimator inconsistent for the conventional parameter of interest: the impact of full treatment o n the fully treated. We develop a test of the identifying assumption u nderlying the standard estimator and consider whether exclusion restri ctions produce identification of the mean impact of the program when t his assumption fails to hold. Finally, we discuss alternative paramete rs of interest in the presence of partial treatment among the dropouts and argue that the conventional parameter is not always the economica lly interesting one. We apply our methods to data from a recent experi mental evaluation of the Job Training Partnership Act (JTPA) program.