Doubly Robust Uniform Confidence Bands for Group-Time Conditional Average Treatment Effects in Difference-in-Differences

This study considers a panel data analysis to examine the heterogeneity in treatment effects with respect to a pre-treatment covariate of interest in the staggered difference-in-differences setting in Callaway and Sant'Anna (2021). Under a set of standard identification conditions, a doubly robust estimand conditional on the covariate identifies the group-time conditional average treatment effect given the covariate. Given this identification result, we propose a three-step estimation procedure based on nonparametric local linear regressions and parametric estimation methods, and develop a doubly robust inference method to construct a uniform confidence band of the group-time conditional average treatment effect function.