A1164
Title: Fixed effects quantile regression via deconvolutional differencing in short panels
Authors: Martin Mugnier - Paris School of Economics (France) [presenting]
Abstract: The focus is on providing point identification results for a quantile regression model with distributional fixed effects. Instead of typical high-level assumptions of nonlinear measurement error models or covariates with dense or large support, a low-level shape restriction is considered: conditional symmetry. Conditional symmetry allows for covariate-heterogeneous quantile effects and arbitrary correlation between the fixed effects and the covariates without ruling out asymmetry of the observed distributions. It is shown how deconvolutional differencing can be applied when at least two measurements are available. Under mild regularity conditions, computationally simple and numerically reliable plug-in estimators are sup-norm consistent and pointwise asymptotically normal as the sample size diverges. Monte Carlo simulations suggest excellent finite-sample performance. The new method is applied to measure the effect of smoking during pregnancy on birth weight.
