内生性
计量经济学
经济
最小二乘函数近似
估计
面板数据
工具变量
二进制数
半参数模型
数学
统计
估计员
非参数统计
管理
算术
作者
Anastasia Semykina,Yimeng Xie,Cynthia Fan Yang,Qiankun Zhou
标识
DOI:10.1016/j.econmod.2024.106661
摘要
This paper investigates the estimation of binary response panel data models with endogenous regressors using semiparametric least squares. The endogeneity arises from an unobserved time-invariant effect and a nonzero correlation between the idiosyncratic error and one or more explanatory variables. Our proposed estimator addresses endogeneity by the correlated random effects and control function approaches. The estimator is shown to be asymptotically normally distributed and to have satisfactory finite sample properties in Monte Carlo experiments. The method's utility is demonstrated through an empirical application that examines the effect of a husband's income on the labor force participation of married women.
科研通智能强力驱动
Strongly Powered by AbleSci AI