摘要Censored Quantile Regression with a Special Regressor

题目:Censored Quantile Regression with a Special Regressor





Qian Wang is currently an Associate Professor at the Research Institute of Economics and Management, Southwestern University of Finance and Economics. She received her Ph.D. at the Hong Kong University of Science and Technology in 2016. Her research interests include topics in econometric theory and applied econometrics.


It is usually difficult to deal with endogeneity in a censored quantile regression model, especially when the endogenous variables are discrete. In this paper we develop an estimator for this model which allows for discrete or continuous endogenous regressors, given an observed special regressor which is conditionally independent of the errors. This estimator is obtained in two stages. The first stage is to separately estimate the coefficient for the special regressor. In the second stage, we apply weighted instrumental variable quantile regression (IVQR) of Chernozhukov and Hansen (2006, 2008) to estimate the other parameters. We show that our estimator is consistent and asymptotically normal. A Monte Carlo study demonstrates our estimator performs well in finite samples.