Advances in Econometrics: Quantile regression, censoring, and the structure of wages

摘要: INTRODUCTION This chapter develops two empirical applications of quantile regression techniques. The first application examines how the returns to schooling have changed from 1979 1987. second union relative wage effect in In both cases our interest is providing a more detailed description conditional distribution wages. based on forming schooling-experience cells, calculating various sample quantiles within each cell, and then using minimum-distance estimator impose parametric form functions. There censoring problem because usual weekly earnings Current Population Survey are topcoded at $999. Our framework makes it very easy apply Powell's (1984, 1986) approach - we only use cells for which below point. correction has substantial estimates some cases. tend increase as pass low high quantiles, substantially higher 1987 than 1979, change fairly uniform across quantiles. does not lend itself since there close 40 covariates. A linear programming algorithm is, however, effective. We find, experienced workers, that declines sharply go similar pattern industry effects several durable manufacturing industries. also generalize functional regressions by Box-Cox transformation. combines with one-dimensional search, appealing equivariance under monotone transformations.