The gender pay gap revisited: Does machine learning offer new insights?

Bonaccolto-Töpfer M, Briel S (2022)

Publication Language: English

Publication Type: Journal article

Publication year: 2022

Journal

Labour Economics Elsevier

Book Volume: 78

Article Number: 102223

DOI: 10.1016/j.labeco.2022.102223

Abstract

This paper analyses gender differences in pay at the mean as well as along the wage distribution in Germany. We estimate the adjusted gender pay gap applying a machine learning method (post-double-LASSO procedure). Comparing results from this method to conventional models in the literature, we find that the estimated gap differs substantially depending on the approach used. The main reason is that the machine learning approach selects numerous interactions and second-order polynomials as well as different covariates at various points of the distribution. This insight suggests that more flexible specifications are needed to estimate gender differences in pay more appropriately.

Authors with CRIS profile

Marina Bonaccolto-Töpfer Lehrstuhl für Volkswirtschaftslehre, insbesondere Arbeitsmarkt- und Regionalpolitik

Related research project(s)

Löhne und Lohndifferenziale Jan. 1, 2000 - Jan. 1, 2003

Involved external institutions

Universität Hohenheim DE Germany (DE)

How to cite

APA:

Bonaccolto-Töpfer, M., & Briel, S. (2022). The gender pay gap revisited: Does machine learning offer new insights? Labour Economics, 78. https://dx.doi.org/10.1016/j.labeco.2022.102223

MLA:

Bonaccolto-Töpfer, Marina, and Stephanie Briel. "The gender pay gap revisited: Does machine learning offer new insights?" Labour Economics 78 (2022).

BibTeX: Download