Title: Estimating a counterfactual wage heavy-tailed distribution using survey data
Authors: Mihaela Catalina Anastasiade - University of Neuchatel (Switzerland)
Alina Matei - University of Neuchatel (Switzerland) [presenting]
Yves Tille - University of Neuchatel (Switzerland)
Abstract: The focus is on the framework of the gender wage modelisation using survey data. The wage of an employee is hypothetically a reflection of their characteristics, such as the education level or the previous work experience. It is possible that a man and a woman with the same characteristics get different salaries. To measure the difference in the gender wages the concept of counterfactual distribution is used. A counterfactual distribution is constructed by reweighting the women wage distribution. We provide two parametric methods to estimate the gender wage quantiles and counterfactual wage quantiles, respectively, and estimate their differences. The goal is to capture the shape of the wage distributions and to go beyond the simple mean differences, by determining the estimator of gender wage discrimination at different quantiles. Since, in general, wage distributions are heavy-tailed, the main interest is to model wages by using heavy-tailed distributions like the GB2 distribution. We illustrate the two proposed methods using the GB2 distribution and compare them with other approaches found in the topic-related literature.