Abstract
In the last decades, there has been increasing awareness of the different types of inequalities that women experience. A very important inequality is the wage gap. Understanding the elements that affect this gap is crucial in order for governments to take the right actions to diminish the gap. It is also important to understand the broader context in which this inequality has evolved over time. In this paper, we develop a causal inference model based on the ideas of Potential Outcome (PO) and Metalearners (ML) to address this important issue. We include a time variable in the causal analysis which helps to determine how the effects have evolved over the last decades. We apply data from 1990 to 2017 from the official government social survey of Chile to fit the models. We then make a deep analysis of each variable using the SHAP framework to see the impact of each variable on the gender wage gap. Sadly, our results indicate that there has been a gap between the earnings of men and women over the last three decades, and the gap actually widened over time. We also find that variable decomposition helps to clarify the different effects as some variables clearly help to diminish this gap. Our results may assist the government of Chile and other organizations to endorse policies that may reduce the gap.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-023-08221-9/MediaObjects/521_2023_8221_Fig12_HTML.png)
Similar content being viewed by others
Data availability
All the data were downloaded and are available from: a) URL:http://observatorio.ministeriodesarrollosocial.gob.cl/encuesta-casen-2017. Note that the url changes with the year.
Notes
http://observatorio.ministeriodesarrollosocial.gob.cl/encuesta-casen-2017 Note that the url varies with the year. The UF is an inflation-adjusted measure of the purchasing power of the Chilean peso. It was worth about 40 USD in early 2022.
http://observatorio.ministeriodesarrollosocial.gob.cl/encuesta-casen-2017 Note that the url changes with the year.
References
Briel S, Töpfer M (2020) “The gender pay gap revisited: Does machine learning offer new insights?,” University of Erlangen-Nürnberg discus-sion paper, vol. 111
Pearl J (2009) Causality. Cambridge University Press, Cambridge
Shapley LS (1953) A value for n-person games. Contributions Theor Games 2(28):307–317
Alatrista-Salas H, Esposito B, Nunez-del Prado M, Valdivieso M (2017) “Measuring the gender discrimination: A machine learning approach,” in 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI), pp. 1–6, IEEE
Bach P, Chernozhukov V, Spindler M (2018) “Closing the US gender wage gap requires understanding its heterogeneity,” http://arxiv.org/abs/1812.04345
Karimian HR, Rouhanizadeh B, Jafari A, Kermanshachi S (2019) “A machine learning framework to identify employees at risk of wage inequality: US Department of Transportation case study,” in Computing in Civil Engineering 2019: Data, Sensing, and Analytics, pp. 26–34, American Society of Civil Engineers Reston, VA
Nie X, Wager S (2017) “Learning objectives for treatment effect estimation,” http://arxiv.org/abs/1712.04912
Künzel SR, Sekhon JS, Bickel PJ, Yu B (2019) Metalearners for estimating heterogeneous treatment effects using machine learning. Proc Nat Acad Sci 116(10):4156–4165
Rubin DB (2005) Causal inference using potential outcomes: design, modeling, decisions. J Am Stat Assoc 100(469):322–331
Wu R, Cheng X (2016) Gender equality in the workplace: The effect of gender equality on productivity growth among the Chilean manufacturers. J Develop Areas 15:257–274
Ñopo H (2007) “The gender wage gap in Chile 1992-2003 from a matching comparisons perspective,” Inter-American Development Bank
Bharadwaj P, De Giorgi G, Hansen D, Neilson CA (2016) The gender gap in mathematics: evidence from Chile. Econ Develop Cultural Change 65(1):141–166
Olson JE (2019) Human capital models and the gender pay gap. Sex Roles 68(3–4):186–197
Blau FD, Kahn LM (2017) The gender wage gap: extent, trends, and explanations. J Econ Literature 55(3):789–865
Kunze A (2018) “The gender wage gap in developed countries,” The Oxford Handbook of Women and the Economy, p. 369
Redmond P, McGuinness S (2019) The gender wage gap in Europe: job preferences, gender convergence and distributional effects. Oxford Bull Econ Stat 81(3):564–587
Hara H (2018) The gender wage gap across the wage distribution in Japan: within-and between-establishment effects. Labour Econ 53:213–229
Tekgüç H, Eryar D, Cindoğlu D (2017) Women’s tertiary education masks the gender wage gap in Turkey. J Labor Res 38(3):360–386
Vaccaro G, Basurto MP, Beltrán A, Montoya M (2022) The gender wage gap in Peru: drivers, evolution, and heterogeneities. Soc Inclusion 10(1):19–34
Si C, Nadolnyak D, Hartarska V et al (2021) The gender wage gap in develo** countries. Appl Econ Financ 8(1):1–12
Kampelmann S, Rycx F, Saks Y, Tojerow I (2018) Does education raise productivity and wages equally? The moderating role of age and gender. IZA J Labor Econ 7(1):1–37
Chevalier A (2007) Education, occupation and career expectations: determinants of the gender pay gap for UK graduates. Oxford Bull Econ Stat 69(6):819–842
Mussida C, Picchio M (2014) The gender wage gap by education in Italy. J Econ Inequal 12(1):117–147
Tyrowicz J, van der Velde L, van Staveren I (2018) Does age exacerbate the gender-wage gap? New method and evidence from Germany, 1984–2014. Feminist Econ 24(4):108–130
Chuang H-L, Lin ES, Chiu S-Y (2018) The gender wage gap in the financial industry: evidence from the interindustry ranking. Int Rev Econ Financ 55:246–258
Sloane CM, Hurst EG, Black DA (2021) College majors, occupations, and the gender wage gap. J Econ Perspect 35(4):223–248
Cortes P, Pan J (2018) “Occupation and gender,” The Oxford Handbook of Women and the Economy, pp. 425–452
Cutillo A, Centra M (2017) Gender-based occupational choices and family responsibilities: the gender wage gap in Italy. Feminist Econ 23(4):1–31
Kauhanen A (2022) “Gender differences in corporate hierarchies,” IZA World of Labor
Bao Z, Li C, Li D (2022) “Hierarchical gender-wage gap: evidence from corporate top managers,” Available at SSRN
Akar G, Balkan B, Tümen S (2014) Overview of firm-size and gender pay gaps in Turkey: the role of informal employment. Ekonomi-tek 2(3):1–21
Chapman SJ, Benis N (2017) Ceteris non paribus: the intersectionality of gender, race, and region in the gender wage gap. Women’s Stud Int Forum 65:78–86
Sánchez R, Finot J, Villena MG (2022) Gender wage gap and firm market power: evidence from Chile. Appl Econ 54(18):2109–2121
Chávez A, Rodríguez-Puello G (2022) Commodity price shocks and the gender wage gap: evidence from the metal mining prices super-cycle in Chile. Resourc Policy 76:102497
Didier N (2021) Does credentialism affect the gender wage gap? Evidence from Chile. Latin Am Policy 12(1):69–96
Oaxaca R (1973) Male-female wage differentials in urban labor markets. Int Econ Rev 14(3):693–709
Blinder AS (1973) Wage discrimination: reduced form and structural estimates. J Human Resourc 8(4):436–455
DiNardo J, Fortin NM, Lemieux T (1996) Labor market institutions and the distribution of wages, 1973–1992: a semiparametric approach. Econ J Econ Soc 45:1001–1044
Juhn C, Murphy KM, Pierce B (1991)“Accounting for the slowdown in black-white wage convergence,” in Workers and Their Wages: Changing Patterns in the United States, pp. 107–143, AEI Press, Washington, D.C
Gelbach JB (2016) When do covariates matter? And which ones, and how much? J Labor Econ 34(2):509–543
Olaya D, Vásquez J, Maldonado S, Miranda J, Verbeke W (2020) Uplift modeling for preventing student dropout in higher education. Decis Support Syst 134:113320
Chen T, Guestrin C (2016) “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, pp. 785–794
Elwert F, Winship C (2014) Endogenous selection bias: the problem of conditioning on a collider variable. Ann Rev Sociol 40:31–53
Griffith GJ, Morris TT, Tudball MJ, Herbert A, Mancano G, Pike L, Sharp GC, Sterne J, Palmer TM, Davey Smith G et al (2020) Collider bias undermines our understanding of COVID-19 disease risk and severity. Nat Commun 11:1–12
Bartram D (2021) Age and life satisfaction: getting control variables under control. Sociology 55(2):421–437
Lundberg SM, Lee S-I (2017) “A unified approach to interpreting model predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4768–4777
Shapley LS (1953) Stochastic games. Proc Nat Acad Sci 39(10):1095–1100
Sang X, **ao W, Zheng H, Yang Y, Liu T (2020) HMMPred: accurate prediction of DNA-binding proteins based on HMM profiles and XGBoost feature selection. Comput Math Methods Med 1384749:2020
Priscilla CV, Prabha DP (2021) A two-phase feature selection technique using mutual information and XGB-RFE for credit card fraud detection. Int J Adv Technol Eng Explor 8(85):1656–1668
Chen MA (2001) Women and informality: a global picture, the global movement. Sais Rev 21(1):71–82
Vahter P, Masso J (2019) The contribution of multinationals to wage inequality: foreign ownership and the gender pay gap. Rev World Econ 155(1):105–148
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Acknowledgements
This study was supported by ANID Fondecyt 1200555 fund.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors have no relevant financial or non-financial interests to disclose.
Consent to Participate
The study does not involve Human Participants. The study does not involve Animals.
Consent to Publish
The authors agreed with the content and gave explicit consent to submit the manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 Description of categorical features
See Tables 4, 5, 6, 7, 8, 9 and 10.
1.2 Resulting variables after drop** for better performance
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kristjanpoller, W., Michell, K. & Olson, J.E. Determining the gender wage gap through causal inference and machine learning models: evidence from Chile. Neural Comput & Applic 35, 9841–9863 (2023). https://doi.org/10.1007/s00521-023-08221-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08221-9