Automatic Debiased Machine Learning for Covariate Shifts

TL;DR

This paper introduces a debiased machine learning estimator for causal and predictive parameters under covariate shift, ensuring reliable inference when training and target populations differ.

Contribution

It develops a novel automatic debiased estimation method that corrects regularization biases in high-dimensional settings using data fusion techniques.

Findings

Estimator is consistent and asymptotically normal.

Method effectively adjusts for covariate shift in empirical studies.

Demonstrated success in policy impact analysis on teen employment.

Abstract

We present machine learning estimators for causal and predictive parameters under covariate shift, where covariate distributions differ between training and target populations. One such parameter is the average effect of a policy that alters the covariate distribution, such as a treatment modifying surrogate covariates used to predict long-term outcomes. Another example is the average treatment effect for a population with a shifted covariate distribution, like the effect of a policy on the treated group. We propose a debiased machine learning method to estimate a broad class of these parameters in a statistically reliable and automatic manner. Our method eliminates regularization biases arising from the use of machine learning tools in high-dimensional settings, relying solely on the parameter's defining formula. It employs data fusion by combining samples from target and training data to eliminate biases. We prove that our estimator is consistent and asymptotically normal. Computational experiments and an empirical study on the impact of minimum wage increases on teen employment--using the difference-in-differences framework with unconfoundedness--demonstrate the effectiveness of our method.