A formal approach to variable selection in difference-in-differences

TL;DR

This paper introduces a formal graphical approach for selecting covariates to justify the parallel trends assumption in difference-in-differences analysis, clarifying when and how covariates should be included.

Contribution

It provides a systematic, graphical criterion-based method for covariate selection in DiD, addressing ad hoc practices and clarifying the role of covariates, including post-treatment variables.

Findings

Unconditional and conditional parallel trends often conflict.

Time-invariant covariates with time-invariant effects can be useful.

Proper covariate adjustment aligns estimation procedures with identification requirements.

Abstract

Difference-in-differences (DiD) identification relies mainly on a parallel trends assumption about untreated potential outcomes. Researchers often relax this assumption by assuming conditional parallel trends within units with the same covariate values. However, the process of selecting which covariates to include in this assumption is often \emph{ad hoc}. We propose a formal approach to select the variables that support conditional parallel trends based on graphical criteria. We show that the parallel trends assumption is rarely justified without conditioning on covariates, and that unconditional and conditional parallel trends can conflict with one another. We also demonstrate that a time-invariant covariate with a time-invariant effect on the outcome, which might not ordinarily be considered a confounder in DiD, may be a useful conditioning variable. We clarify that adjustment for a post-treatment covariate depends on what causes that covariate to change. Extending our framework to multiple time periods, we distinguish between treatment type and rollout strategy and examine the problem of treatment-confounder feedback. On the estimation side, we argue that the difficulty of incorporating covariates in DiD, often framed as an estimator problem, is more accurately understood as a misalignment between the adjustment set used by the estimator and the adjustment set required for identification. This misalignment affects several popular estimation procedures, and resolving it requires not a change of estimator, but a change in how covariates enter the estimation procedure. We show how to achieve this alignment for all estimators we evaluate.