Flexible estimation of wage distributions in the presence of covariates

We propose an estimator of conditional wage distributions that is based on a piecewise-linear specification of the conditional hazard function. Under a minimal set of assupmptions, the estimator is flexible enough to capture almost any underlying relationship. It is not affected by the curse of dimensionality and allows to derive conditional Lorenz curves and Gini indices. The methodology is applied to investigate the trends in wages in Spain in 1994-1999. Our estimation results show that the “overeducation” phenomenon intensified in Spain in this period. J.E.L. Classification Numbers: C14, J31.