Estimation of an unbalanced panel data Tobit model with interactive effects. (September 2018)

• Record Type: Journal Article
• Authors: Ye, Xiaoqing; Xu, Juan; Wu, Xiangjun
• Is Part Of: Journal of choice modelling. Volume 28(2018)
• Page Start: 108
• Page End: 123
• Publication Date: 2018-09
• Subjects: Panel data Tobit model -- Interactive effects -- Missing data -- Maximum likelihood -- ECM; Decision making -- Periodicals; Social choice -- Periodicals; Decision making; Social choice; Periodicals; 302.13
• DOI: 10.1016/j.jocm.2018.04.004
• Languages: English
• ISSNs: 1755-5345

Abstract

Abstract: Unbalanced panel data or panel data with missing observations are common in empirical research. In this paper, we consider an unbalanced panel data Tobit model with interactive effects, and provide an estimator based on the iteration of Tobit factor analysis and maximum likelihood estimation. Monte Carlo studies are carried out to investigate the finite sample performance of the proposed method in comparison with other candidate methods. The results show that the finite sample performance of the proposed method is satisfactory under different Mont Carlo designs. We also apply our method to study female labor supply using an unbalanced panel data set from the Chinese Family Panel Studies (CFPS). Highlights: We consider an unbalanced panel data Tobit model with interactive effects. We provide an estimator based on the iteration of Tobit factor analysis and maximum likelihood estimation. The good finite sample properties of the estimators are shown by Monte Carlo analysis. We apply the proposed estimator to study the female labor supply in Shanghai, China.