The distributional impacts of social programs

Abstract

We illustrate the use of nonparametric quantile regression in examining the impacts of social programs on the distributions of noncategorical outcome measures. We apply the method to earnings effects and income effects in four evaluations of employment and training programs for welfare recipients. The distributional impact estimates yield pictures of program impacts that are different from those yielded by simple mean impact estimates, especially for income. The distributional impact estimates also assist in differentiating the effects of programs using similar activities but organizing those activities to achieve different goals. Accurately estimating effects at the tail of a distribution remains a problem.