带有固定效应的半参数面板数据模型的回归样条估计  

Regression Splines Estimation for Semiparametric Panel Data Models with Fixed Effects

作　　者：吕洋 朱仲义[1] LYU Yang;ZHU ZhongYi(Department of Statistics,School of Management,Fudan University,Shanghai,200433,China)

机构地区：[1]复旦大学管理学院统计系,上海200433

出　　处：《应用概率统计》2018年第1期84-94,共11页Chinese Journal of Applied Probability and Statistics

基　　金：国家自然科学基金项目(批准号:11671096;11731011)资助

摘　　要：本文研究了带有固定效应的半参数面板数据模型的B样条估计.给出了非参数函数m的B样条估计的渐近偏差的表达式.我们的研究结果表明,B样条估计量的渐近偏差不依赖于工作协方差矩阵.通过蒙特卡洛模拟,证实了我们的结论.In this paper,we study the asymptotic behavior of the B-spline estimator for semiparametric panel data model with fixed effects.We give explicit expression for the asymptotic bias of B-spline estimator for nonparametric function m.Our study shows that the asymptotic bias of the B-spline estimator does not depend on the working correlation matrix.Simulations are conducted to demonstrate our conclusion.

关 键 词：B-样条 面板数据 固定效应 半参数模型 

分 类 号：O212.4[理学—概率论与数理统计]