Using Machine Learning Methods to Estimate the Gender Wage Gap

Rachel Joy Forshaw; Vsevolod Iakovlev; Mark Edwin Schaffer; Cristina Tealdi

doi:10.1007/978-3-031-43601-7_6

Using Machine Learning Methods to Estimate the Gender Wage Gap

Rachel Joy Forshaw, Vsevolod Iakovlev, Mark Edwin Schaffer, Cristina Tealdi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Gender Wage Gap (GWG) is a classic topic in labour economics. Simply put, how do we explain the observed gap in earnings between men and women? Traditionally the GWG has been estimated using regression models based on Mincer-type wage equations controlling for individual, job and firm characteristics. Recently the literature has shifted towards understanding the relevance of methodological choices in estimating the GWG, including new machine learning (ML) techniques. This paper contributes to the discussion by exploring the alternative machine learning techniques to estimate the GWG. Specifically, we illustrate how to implement the proposal of Ahrens et al. [3] to use “stacking regression” in combination with the “Double-Debiased Machine Learning” methodology of Chernozhukov et al. [12].

Original language	English
Title of host publication	Machine Learning for Econometrics and Related Topics
Publisher	Springer
Pages	109–129
Number of pages	21
ISBN (Electronic)	9783031436017
ISBN (Print)	9783031436000
DOIs	https://doi.org/10.1007/978-3-031-43601-7_6
Publication status	Published - 2 Jun 2024
Event	16th International Conference of Thailand Econometric Society 2023 - Chiang Mai, Thailand Duration: 4 Jan 2023 → 6 Jan 2023

Publication series

Name	Studies in Systems, Decision and Control
Volume	508
ISSN (Print)	2198-4182
ISSN (Electronic)	2198-4190

Conference

Conference	16th International Conference of Thailand Econometric Society 2023
Abbreviated title	TES 2023
Country/Territory	Thailand
City	Chiang Mai
Period	4/01/23 → 6/01/23

Keywords

Gender wage gap
Labour economics
Machine learning
Econometrics

ASJC Scopus subject areas

Computer Science (miscellaneous)
Control and Optimization
Decision Sciences (miscellaneous)
Economics, Econometrics and Finance (miscellaneous)
Control and Systems Engineering
Automotive Engineering
Social Sciences (miscellaneous)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-43601-7_6

Cite this

@inproceedings{ab670090ce1442bd962210080b7c5968,

title = "Using Machine Learning Methods to Estimate the Gender Wage Gap",

abstract = "The Gender Wage Gap (GWG) is a classic topic in labour economics. Simply put, how do we explain the observed gap in earnings between men and women? Traditionally the GWG has been estimated using regression models based on Mincer-type wage equations controlling for individual, job and firm characteristics. Recently the literature has shifted towards understanding the relevance of methodological choices in estimating the GWG, including new machine learning (ML) techniques. This paper contributes to the discussion by exploring the alternative machine learning techniques to estimate the GWG. Specifically, we illustrate how to implement the proposal of Ahrens et al. [3] to use “stacking regression” in combination with the “Double-Debiased Machine Learning” methodology of Chernozhukov et al. [12].",

keywords = "Gender wage gap, Labour economics, Machine learning, Econometrics",

author = "Forshaw, {Rachel Joy} and Vsevolod Iakovlev and Schaffer, {Mark Edwin} and Cristina Tealdi",

year = "2024",

month = jun,

day = "2",

doi = "10.1007/978-3-031-43601-7_6",

language = "English",

isbn = "9783031436000",

series = "Studies in Systems, Decision and Control",

publisher = "Springer",

pages = "109–129",

booktitle = "Machine Learning for Econometrics and Related Topics",

note = "16th International Conference of Thailand Econometric Society 2023, TES 2023 ; Conference date: 04-01-2023 Through 06-01-2023",

}

Forshaw, RJ, Iakovlev, V, Schaffer, ME & Tealdi, C 2024, Using Machine Learning Methods to Estimate the Gender Wage Gap. in Machine Learning for Econometrics and Related Topics. Studies in Systems, Decision and Control, vol. 508, Springer, pp. 109–129, 16th International Conference of Thailand Econometric Society 2023, Chiang Mai, Thailand, 4/01/23. https://doi.org/10.1007/978-3-031-43601-7_6

TY - GEN

T1 - Using Machine Learning Methods to Estimate the Gender Wage Gap

AU - Forshaw, Rachel Joy

AU - Iakovlev, Vsevolod

AU - Schaffer, Mark Edwin

AU - Tealdi, Cristina

PY - 2024/6/2

Y1 - 2024/6/2

N2 - The Gender Wage Gap (GWG) is a classic topic in labour economics. Simply put, how do we explain the observed gap in earnings between men and women? Traditionally the GWG has been estimated using regression models based on Mincer-type wage equations controlling for individual, job and firm characteristics. Recently the literature has shifted towards understanding the relevance of methodological choices in estimating the GWG, including new machine learning (ML) techniques. This paper contributes to the discussion by exploring the alternative machine learning techniques to estimate the GWG. Specifically, we illustrate how to implement the proposal of Ahrens et al. [3] to use “stacking regression” in combination with the “Double-Debiased Machine Learning” methodology of Chernozhukov et al. [12].

AB - The Gender Wage Gap (GWG) is a classic topic in labour economics. Simply put, how do we explain the observed gap in earnings between men and women? Traditionally the GWG has been estimated using regression models based on Mincer-type wage equations controlling for individual, job and firm characteristics. Recently the literature has shifted towards understanding the relevance of methodological choices in estimating the GWG, including new machine learning (ML) techniques. This paper contributes to the discussion by exploring the alternative machine learning techniques to estimate the GWG. Specifically, we illustrate how to implement the proposal of Ahrens et al. [3] to use “stacking regression” in combination with the “Double-Debiased Machine Learning” methodology of Chernozhukov et al. [12].

KW - Gender wage gap

KW - Labour economics

KW - Machine learning

KW - Econometrics

UR - http://www.scopus.com/inward/record.url?scp=85198401039&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-43601-7_6

DO - 10.1007/978-3-031-43601-7_6

M3 - Conference contribution

SN - 9783031436000

T3 - Studies in Systems, Decision and Control

SP - 109

EP - 129

BT - Machine Learning for Econometrics and Related Topics

PB - Springer

T2 - 16th International Conference of Thailand Econometric Society 2023

Y2 - 4 January 2023 through 6 January 2023

ER -

Using Machine Learning Methods to Estimate the Gender Wage Gap

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Embargoed Document

Fingerprint

Cite this