L-Estimation Approach to Tobit Models with Endogeneity and Weakly Dependent Errors
arXiv:2405.19145
Abstract
This article introduces an L-estimator for the semiparametric Tobit model with endogenous regressors. The estimation procedure follows a two-stage approach: the first stage employs least squares, while the second stage utilizes the L-estimation technique. We establish the large-sample properties of the proposed estimators under weakly dependent data. The utility of the proposed methodology is demonstrated for various simulated data and a benchmark real data set.
In the present version of the article, the following significant changes have been made. (1) The mathematical assumptions are more elaborately written. (2) The effect of the first stage has been incorporated in the theoretical results. (3) The dependent structure has been modified