Formål
The purpose of the project is to decompose the Danish gender wage gap over time into various explainable factors, particularly focusing on the extent to which the gap is attributable to different career paths versus wage discrepancies within the same career path.
The study population encompasses the entire Danish wage-earning population in the year 2021, with data tracked back as far as records allow.
Metode
The methodology involves using a transformer model to create representations of career trajectories, complemented by a neural network trained to estimate an expected wage for men and women, respectively, given a career trajectory representation. This will allow us to estimate the within-career gender wage gap.