Pre-Event Trends in the Panel Event-Study Design

TLDR

The study examines a linear panel event‑study design where unobserved confounds may influence both the outcome and the policy variable. The authors aim to establish sufficient conditions that identify the policy’s causal effect by leveraging covariates linked to the policy only through confounds. They derive linear moment equations and estimate the policy effect via two‑stage least squares, ensuring valid causal inference even when endogeneity induces pre‑event trends. Simulation results show that alternative methods perform poorly compared to the proposed approach. JEL codes: C23, C26.

Abstract

We consider a linear panel event-study design in which unobserved confounds may be related both to the outcome and to the policy variable of interest. We provide sufficient conditions to identify the causal effect of the policy by exploiting covariates related to the policy only through the confounds. Our model implies a set of moment equations that are linear in parameters. The effect of the policy can be estimated by 2SLS, and causal inference is valid even when endogeneity leads to pre-event trends (“pre-trends”) in the outcome. Alternative approaches perform poorly in our simulations. (JEL C23, C26)