CMStatistics 2017: Start Registration
View Submission - CFE
A0166
Title: Semiparametric estimation of a sample selection model with binary endogenous regressors Authors:  Patricia Moreno - Universidad de Cantabria (Spain)
Juan Manuel Rodriguez-Poo - Universidad de Cantabria (Spain) [presenting]
Abstract: An alternative method is provided for estimating the impact of an endogenous treatment effect in the presence of sample selection. The estimation method is based on a two-step approach: in the first step, we use parametric regression for estimating the treatment and selection variables, and in the second one we propose an weighted pairwise differences estimator by using the first ones as control functions accounting for both endogeneity and sample selection but assuming an unknown distribution of the errors in the main equation. The proposed estimator is shown to be consistent and asymptotically normal. An empirical application is presented to demonstrate the usefulness of our method.