Simulation-Based Sensitivity Analysis for Matching Estimators

This article presents a Stata program (sensatt) that implements the sensitivity analysis for matching estimators proposedb y Ichino, Mealli and Nannicini (2007). The analysis simulates a potential confounder in order to assess the robustness of the estimatedtrea tment effects with respect to deviations from the Conditional Independence Assumption (CIA). The program makes use of the commands for propensity-score matching (att*) developed by Becker and Ichino (2002). An example is given by using the National SupportedW ork (NSW) demonstration, widely known in the program evaluation literature.