Regularizing Double Machine Learning in Partially Linear Endogenous Models

TL;DR

This paper introduces regsDML, a regularization scheme for double machine learning in partially linear endogenous models, producing narrower confidence intervals and improved finite sample performance.

Contribution

The paper proposes regsDML, a data-driven regularization method that combines TSLS DML and regularization estimators, enhancing inference in partially linear endogenous models.

Findings

regsDML converges at the parametric rate

It is asymptotically Gaussian distributed

It exhibits better finite sample properties than traditional DML

Abstract

The linear coefficient in a partially linear model with confounding variables can be estimated using double machine learning (DML). However, this DML estimator has a two-stage least squares (TSLS) interpretation and may produce overly wide confidence intervals. To address this issue, we propose a regularization and selection scheme, regsDML, which leads to narrower confidence intervals. It selects either the TSLS DML estimator or a regularization-only estimator depending on whose estimated variance is smaller. The regularization-only estimator is tailored to have a low mean squared error. The regsDML estimator is fully data driven. The regsDML estimator converges at the parametric rate, is asymptotically Gaussian distributed, and asymptotically equivalent to the TSLS DML estimator, but regsDML exhibits substantially better finite sample properties. The regsDML estimator uses the idea of k-class estimators, and we show how DML and k-class estimation can be combined to estimate the linear coefficient in a partially linear endogenous model. Empirical examples demonstrate our methodological and theoretical developments. Software code for our regsDML method is available in the R-package dmlalg.