Inference on Optimal Treatment Assignments

Abstract

We consider inference on optimal treatment assignments. Our methods allow for inference on the treatment assignment rule that would be optimal given knowledge of the population treatment eect in a general setting. The procedure uses multiple hypothesis testing methods to determine a subset of the population for which assignment to treatment can be determined to be optimal after conditioning on all available information, with a prespecied level of condence. A monte carlo study conrms that the inference procedure has good small sample behavior. We apply the method to study the Mexican conditional cash transfer program Progresa.