Decomposing the Gender Wage Gap in the Netherlands with Sample Selection Adjustments

In this paper, we use quantile regression decomposition methods to analyzethe gender gap between men and women who work full time in the Nether-lands. Because the fraction of women working full time in the Netherlands isquite low, sample selection is a serious issue. In addition to shedding light onthe sources of the gender gap in the Netherlands, we make two methodolog-ical contributions. First, we prove that the Machado-Mata quantile regres-sion decomposition procedure yields consistent and asymptotically normalestimates of the quantiles of the counterfactual distribution that it is de-signed to simulate. Second, we show how the technique can be extended toaccount for selection.We find that there is a positive selection of women into full-time workin the Netherlands, i.e., women who get the greatest return to working fulltime do work full time. We find that about two-thirds of this selection isdue to observables such as education and experience with the remainder dueto unobservables. Our decompositions show that the majority of the genderlog wage gap is due to differences between men and women in returns tolabor market characteristics rather than to differences in the characteristics.This is true across the wage distribution, particularly in the top half of thedistribution.