Quantile regression evidence on Italian education returns

This study intends to provide some updated empirical evidenceon Italian Education Returns through Quantile Regression. Such
a methodology enables us to explore the (Quantile Treatment) Effect
of Schooling on the (shape of) income conditional distribution
(viewed as reflecting the distribution of unobservable ability), and
to analyze indirectly the education-ability interaction in the generation
of human capital, and its effect on earnings. We obtain estimates
displaying a U-shaped pattern, i.e. higher returns at the highest
and lowest quantiles of income, suggesting substitution among
human capital factors for low ability individuals, and complementarity
for high ability earners. [JEL codes: C21, I20, J24, J31]