SENSIMATCH: Stata module to provide data-driven sensitivity analysis for Matching estimator

sensimatch provides a sensitivity test for checking the robustness of the selection-on-observables assumption in treatment effect observational studies, both within a regression adjustment and a propensity-score matching approach. Rooted in the machine learning literature, this sensitivity analysis is based on a "leave-one-covariate-out" (LOCO) approach. This method recalls a bootstrap over different subsets of covariates, and simulates various estimation scenarios to be compared with the baseline results obtained by the analyst. The main output of sensimatch is graphical, thus providing the user with an easy-to-interpret robustness check of his/her study results.