Abstract
This note shows how the Shapley value can be applied to the regression-based methods that are often used to decompose changes in wage distributions. The method remedies the path-dependency exhibited by existing approaches that compute the contributions due to (1) changes in sample observable characteristics, (2) changes in the return of characteristics, (3) changes in the distribution of unobservable characteristics.
Full Text
Submitted Version (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call