Evaluating policy changes that occur everywhere at the same time is difficult because of the lack of a clear counterfactual. Hoping to address this problem, researchers often proxy for differential exposure using some observed characteristic in the pre-treatment period. As a cautionary tale of...

<i>This paper was motivated by <a href="/papers/w19795">an earlier NBER working paper</a>. The authors of that paper have posted <a href="https://www.nber.org/data-appendix/w19795/KL_Response_to_JJK-JBES-July_2018_FINAL.pdf">a response to this paper</a>. <a href=" /papers/w24857">Another NBER working paper</a> addresses issues in both of these papers.</i>