Answers are grounded in this paper and cite their sources.
We propose a method for estimating the mean impact of an assigned social program when it is not feasible to do a pre-intervention baseline survey but it is feasible to track ex-participants. In our triple-difference estimator, measured outcome changes are compared between continuing participants and matched ex-participants, after netting out the outcome changes for a matched comparison group who never participated. With sufficient followup observations one can test the joint conditions required for correctly identifying the gains to current participants. We apply the method to a workfare program in Argentina. Significant impacts on participants’ current incomes are revealed.
No takes yet. Share an insight, caveat, or question.
Ravallion et al. (2005) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: