Decomposing Inequalities using Machine Learning and Overcoming Common Support Issues

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flachaire, Emmanuel, Picard, Bertille
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918205995352064
author Flachaire, Emmanuel
Picard, Bertille
author_facet Flachaire, Emmanuel
Picard, Bertille
contents The Kitagawa-Oaxaca-Blinder decomposition splits the difference in means between two groups into an explained part, due to observable factors, and an unexplained part. In this paper, we reformulate this framework using potential outcomes, highlighting the critical role of the reference outcome. To address limitations like common support and model misspecification, we extend Neumark's (1988) weighted reference approach with a doubly robust estimator. Using Neyman orthogonality and double machine learning, our method avoids trimming and extrapolation. This improves flexibility and robustness, as illustrated by two empirical applications. Nevertheless, we also highlight that the decomposition based on the Neumark reference outcome is particularly sensitive to the inclusion of irrelevant explanatory variables.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13433
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decomposing Inequalities using Machine Learning and Overcoming Common Support Issues
Flachaire, Emmanuel
Picard, Bertille
Econometrics
The Kitagawa-Oaxaca-Blinder decomposition splits the difference in means between two groups into an explained part, due to observable factors, and an unexplained part. In this paper, we reformulate this framework using potential outcomes, highlighting the critical role of the reference outcome. To address limitations like common support and model misspecification, we extend Neumark's (1988) weighted reference approach with a doubly robust estimator. Using Neyman orthogonality and double machine learning, our method avoids trimming and extrapolation. This improves flexibility and robustness, as illustrated by two empirical applications. Nevertheless, we also highlight that the decomposition based on the Neumark reference outcome is particularly sensitive to the inclusion of irrelevant explanatory variables.
title Decomposing Inequalities using Machine Learning and Overcoming Common Support Issues
topic Econometrics
url https://arxiv.org/abs/2511.13433