Debiasing Machine-Learning- or AI-Generated Regressors in Partial Linear Models

40 Pages Posted: 30 Nov 2023 Last revised: 22 Feb 2024

See all articles by Jingwen Zhang

Jingwen Zhang

University of Washington

Wendao Xue

University of Texas at Austin - Department of Information, Risk and Operations Management; University of Washington - Department of Economics

Yifan Yu

The University of Texas at Austin; Amazon

Yong Tan

University of Washington - Michael G. Foster School of Business

Date Written: November 17, 2023

Abstract

Researchers are increasingly leveraging machine learning (ML) or artificial intelligence technologies (AI) to predict feature variables and use them as regressors in subsequent econometric models. However, because ML/AI predictions are imperfect, these generated regressors would inevitably contain measurement errors. The direct use of such regressors in subsequent econometric models can result in biased estimation, ultimately leading to inaccurate conclusions. In light of this, we examine the problem of debiasing ML/AI-generated regressors in partial linear regression models. We propose estimators that utilize Two-Stage Least Square (TSLS) and Generalized Method of Moments (GMM) under the Double Machine Learning (DML) framework. We demonstrate the asymptotic consistency and normality of our estimators. Moreover, we conduct extensive Monte Carlo simulations and empirical applications to show the outperformance of our estimators compared with other methods. Our work advances causal inference in addressing measurement error problems arising from ML/AI-generated regressors in partial linear models and hence provides valuable practical implications for designing experimental systems and overcoming ML/AI biasedness.

Keywords: causal inference, double machine learning, AI, measurement error, partial linear

Suggested Citation

Zhang, Jingwen and Xue, Wendao and Yu, Yifan and Tan, Yong, Debiasing Machine-Learning- or AI-Generated Regressors in Partial Linear Models (November 17, 2023). Available at SSRN: https://ssrn.com/abstract=4636026 or http://dx.doi.org/10.2139/ssrn.4636026

Jingwen Zhang (Contact Author)

University of Washington ( email )

Box 353200
Seattle, WA 98195-3200
United States

Wendao Xue

University of Texas at Austin - Department of Information, Risk and Operations Management ( email )

CBA 5.202
Austin, TX 78712
United States

University of Washington - Department of Economics ( email )

Box 353330
Seattle, WA 98195-3330
United States

Yifan Yu

The University of Texas at Austin ( email )

2317 Speedway
Austin, TX Texas 78712
United States

Amazon ( email )

Yong Tan

University of Washington - Michael G. Foster School of Business ( email )

Box 353226
Seattle, WA 98195-3226
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
257
Abstract Views
635
Rank
225,583
PlumX Metrics