Staggered Adoption DiD Designs with Misclassification and Anticipation

TL;DR

This paper analyzes how misclassification and anticipation affect the estimation of treatment effects in staggered adoption DiD designs, proposing modified estimators and tests to improve causal inference.

Contribution

It introduces new estimators that correct bias caused by misclassification and anticipation in staggered DiD models, along with tests for assumption violations.

Findings

Standard estimators are biased under misclassification and anticipation.

Proposed estimators recover true treatment effects.

Application demonstrates practical relevance of methods.

Abstract

This paper examines the identification and estimation of treatment effects in staggered adoption designs -- a common extension of the canonical Difference-in-Differences (DiD) model to multiple groups and time-periods -- in the presence of (time varying) misclassification of the treatment status as well as of anticipation. We demonstrate that standard estimators are biased with respect to commonly used causal parameters of interest under such forms of misspecification. To address this issue, we provide modified estimators that recover the Average Treatment Effect of observed and true switching units, respectively. Additionally, we suggest two moment based specification tests aimed at detecting Parallel Trends violations in pre-treatment periods as well as the timing and extent of misclassification and anticipation effects. We illustrate the proposed methods with an application to the effects of an anti-cheating policy on school mean test scores in high stakes national exams in Indonesia.