Inference for Heterogeneous Effects using Low-Rank Estimation of Factor Slopes

Victor Chernozhukov; Christian Hansen; Yuan Liao; Yinchu Zhu

doi:10.1162/REST.a.1735

Back

Inference for Heterogeneous Effects using Low-Rank Estimation of Factor Slopes

Journal article

Peer reviewed

Inference for Heterogeneous Effects using Low-Rank Estimation of Factor Slopes

Victor Chernozhukov, Christian Hansen, Yuan Liao and Yinchu Zhu

The review of economics and statistics, pp.1-45

03/24/2026

DOI: 10.1162/REST.a.1735

View Online

Abstract

We study a panel data model with heterogeneous effects, allowing slopes to vary across individuals and time. To reduce dimensionality, we assume these slopes follow a factor structure, so slope matrices can be estimated via low-rank regularized regression. We propose a multi-step estimation procedure incorporating sample splitting and partialing-out to enable valid inference after penalized estimation. We establish the asymptotic normality of the resulting estimator, facilitating inference for individualtime- specific effects and their cross-sectional averages. The method’s performance is illustrated through simulations and an empirical application.

Details

Title: Subtitle: Inference for Heterogeneous Effects using Low-Rank Estimation of Factor Slopes
Creators: Victor Chernozhukov - IIT@MIT
Christian Hansen - University of Chicago
Yuan Liao - Rutgers, The State University of New Jersey
Yinchu Zhu - Brandeis University
Resource Type: Journal article
Publication Details: The review of economics and statistics, pp.1-45
DOI: 10.1162/REST.a.1735
ISSN: 0034-6535
eISSN: 1530-9142
Publisher: MIT Press
Language: English
Electronic publication date: 03/24/2026
Academic Unit: Economics
Record Identifier: 9985148849302771

Metrics

1 Record Views