A0178
Title: Unconditional quantile partial effects via conditional quantile regression
Authors: Antonio Galvao - Michigan State University (United States) [presenting]
Abstract: Semi-parametric procedures are developed for the estimation and inference of unconditional quantile partial effects using quantile regression coefficients. The main result is based on the fact that, for continuous covariates, unconditional quantile effects are a weighted average of conditional ones. We propose a two-step estimator for the unconditional effects. In the first step, one estimates a structural quantile regression model, and in the second stage, a non-parametric regression is applied. We establish the asymptotic properties of the estimator. Inference is based on estimation of the asymptotic variance of the estimator. Monte Carlo simulations show evidence that the estimator has very good finite sample performance and is robust to the selection of bandwidth and kernel. To illustrate the proposed methods, we study the canonical study of returns to education to estimate unconditional effects.
