Doubly Robust Semiparametric Difference-in-Differences Estimators with High-Dimensional Data

TL;DR

This paper introduces a doubly robust semiparametric difference-in-differences estimator designed for high-dimensional data, enabling accurate heterogeneous treatment effect estimation even with many regressors.

Contribution

It develops a novel two-stage estimator that is robust to model misspecification, accommodates machine learning methods, and provides bias correction for valid inference.

Findings

Performs well in finite sample simulations

Successfully applied to analyze the effect of the Fair Minimum Wage Act

Provides an R package for implementation

Abstract

This paper proposes a doubly robust two-stage semiparametric difference-in-difference estimator for estimating heterogeneous treatment effects with high-dimensional data. Our new estimator is robust to model miss-specifications and allows for, but does not require, many more regressors than observations. The first stage allows a general set of machine learning methods to be used to estimate the propensity score. In the second stage, we derive the rates of convergence for both the parametric parameter and the unknown function under a partially linear specification for the outcome equation. We also provide bias correction procedures to allow for valid inference for the heterogeneous treatment effects. We evaluate the finite sample performance with extensive simulation studies. Additionally, a real data analysis on the effect of Fair Minimum Wage Act on the unemployment rate is performed as an illustration of our method. An R package for implementing the proposed method is available on Github.