Estimation of a Sample Selection Model with a Binary Dependent variable Under Nonparametric Selection Mechanisim
2014/12/02
研討會日期 : 2014-12-02
時間 : 14:30
主講人 : Professor Yahong Zhou
主持人 : Professor Yeutien Chou
地點 : Conference Room B110
演講者簡介 : Professor Zhou received his Ph.D. in Economics from Hong Kong University of Science and Technology in 2005. He is currently an Associate Professor at The School of Economics of SUFE (Shanghai University of Finance and Economics). His research field is Micro Econometrics.
演講摘要 : In this paper, we consider an estimation procedure for a sample seclection model with a binary dependent variable with possible endogenous regressors. Under semiparametric framework, we don't impose the parametric specification of the error distribution and the functional form in the selection equation, which largely reduces the risk of model misspecification. Similar with Rothe (2009), control function approach is used to account for possible endogeneity. In this paper we give the identification conditions for this model and propose a two-step maximum likelihood estimator with the first step being a nonparametric regression for the selection variable; and the second step uses the semiparametric log-likelihood method to estimate the coefficients in the binary outcome equation. The proposed estimator is shown to be consistent and asymptotically normally distributed. It also performs well in our simulation study.
