Inference on the Best Policies with Many Covariates

TL;DR

This paper introduces a resampling-based inference method that corrects for winner's curse and handles many covariates, providing accurate evaluation of the best policies in large datasets.

Contribution

It proposes a novel, robust inference procedure that addresses winner's curse and covariate complexity in policy effect estimation, with proven asymptotic validity.

Findings

Accurate point estimates and confidence intervals achieved.

Method performs well in finite-sample Monte Carlo simulations.

Effective in empirical studies on charitable giving and employment programs.

Abstract

Understanding the impact of the most effective policies or treatments on a response variable of interest is desirable in many empirical works in economics, statistics and other disciplines. Due to the widespread winner's curse phenomenon, conventional statistical inference assuming that the top policies are chosen independent of the random sample may lead to overly optimistic evaluations of the best policies. In recent years, given the increased availability of large datasets, such an issue can be further complicated when researchers include many covariates to estimate the policy or treatment effects in an attempt to control for potential confounders. In this manuscript, to simultaneously address the above-mentioned issues, we propose a resampling-based procedure that not only lifts the winner's curse in evaluating the best policies observed in a random sample, but also is robust to the presence of many covariates. The proposed inference procedure yields accurate point estimates and valid frequentist confidence intervals that achieve the exact nominal level as the sample size goes to infinity for multiple best policy effect sizes. We illustrate the finite-sample performance of our approach through Monte Carlo experiments and two empirical studies, evaluating the most effective policies in charitable giving and the most beneficial group of workers in the National Supported Work program.