Policy Learning with Confidence
Econometrics
2026-01-21 v3 Methodology
Abstract
This paper introduces a rule for policy selection in the presence of estimation uncertainty, explicitly accounting for estimation risk. The rule belongs to the class of risk-aware rules on the efficient decision frontier, characterized as policies offering maximal estimated welfare for a given level of estimation risk. Among this class, the proposed rule is chosen to provide a reporting guarantee, ensuring that the welfare delivered exceeds a threshold with a pre-specified confidence level. We apply this approach to the allocation of a limited budget among social programs using estimates of their marginal value of public funds and associated standard errors.
Cite
@article{arxiv.2502.10653,
title = {Policy Learning with Confidence},
author = {Victor Chernozhukov and Sokbae Lee and Adam M. Rosen and Liyang Sun},
journal= {arXiv preprint arXiv:2502.10653},
year = {2026}
}
Comments
40 pages, 3 figures