Closing the U.S. gender wage gap requires understanding its heterogeneity

Abstract

In 2016, the majority of full-time employed women in the U.S. earned significantly less than comparable men. The extent to which women were affected by gender inequality in earnings, however, depended greatly on socio-economic characteristics, such as marital status or educational attainment. In this paper, we analyzed data from the 2016 American Community Survey using a high-dimensional wage regression and applying double lasso to quantify heterogeneity in the gender wage gap. We found that the gap varied substantially across women and was driven primarily by marital status, having children at home, race, occupation, industry, and educational attainment. We recommend that policy makers use these insights to design policies that will reduce discrimination and unequal pay more effectively.

The Gender Pay Gap Revisited with Big Data: Do Methodological Choices Matter?

“…This is in line with substantial heterogeneity in estimated pay gaps that is widely acknowledged in the literature (e.g. Bach et al, 2018;Chernozhukov et al, 2018a;Goldin, 2014).…”

“…A possible disadvantage of this approach is that we do not obtain estimates of the parameters α BO and β BO , since they are not required to estimate δ BO . Alternatively, Bach et al (2018) propose a procedure that is based on post-double-selection, but is more flexible and allows us to obtain estimates of selected parameters in α BO and β BO .…”

“…Any heterogeneity that is not captured by this may bias estimates of the mean gender pay gap. This is particularly relevant, because heterogeneity in gender pay gaps is widely acknowledged in the literature (see, e.g., Bach et al, 2018; Barón and Cobb-Clark, 2010; Bonjour and Gerfin, 2001;Chernozhukov et al, 2013Chernozhukov et al, , 2018aGoldin, 2014).…”

“…Relatedly, Barsky et al (2002) and Graham et al (2016) study the sensitivity of black-white gaps with regard to different parametric and semi-parametric estimators. Bach et al (2018) and Briel and Töpfer (2020) apply machine learning methods for model specification using the post-double-selection procedure. However, none of these studies provides a comparable large-scale systematic analysis of gender pay gap estimates with regard to our considered methodological choices.…”

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

“…This paper uses the post-double-LASSO estimator for estimation of the GPG. Closest related to this study is the work of Bach et al (2018) focusing on heterogeneity in the US GPG using double-LASSO. Compared to our paper, they introduce heterogeneity not in terms of relations between different control variables but directly through multiple interactions with the female dummy.…”