A0560
Title: Nonparametric and semiparametric estimation of upward rank mobility curves
Authors: Tsung-Chih Lai - National Chung Cheng University (Taiwan) [presenting]
Jia-Han Shih - National Central University (Taiwan)
Yi-Hau Chen - Academia Sinica (Taiwan)
Abstract: A novel approach to measuring upward mobility in income ranks across generations that considers the heterogeneity within income classes is presented. Specifically, a previous measure is extended to its continuous form, and a tuning parameter-free nonparametric estimator based on the empirical beta copula is proposed. The estimator is shown to be a particular case of the empirical Bernstein copula-based estimator, with all polynomial degrees equal to the sample size. In addition, a semiparametric distribution regression-based estimator is suggested for conditional mobility with unconditional (or fixed) ranks, which converges weakly to a Gaussian process at the parametric rate and has better finite-sample properties. Applying these methods to the National Longitudinal Survey of Youth data shows strong evidence of stochastic dominance relations in upward rank mobility between blacks and whites in the United States.