研究了纵向数据下部分线性EV函数关系模型.应用一般非参数权函数法和广义最小二乘法给出了未知参数β,误差方差σ^2以及未知函数g(·)的估计.在一般的条件下,证明了β,σ^2估计的渐近正态性,同时也给出了未知函数g(·)估计的收敛速度,其结果是独立数据情形下相应结果的推广.
In this paper, a partially linear EV functional relationship model under longitudinal data is considered. By using a non-parametric kernel weight function and generalized least square method, the estimators of unknown parameter β, the variance of errors σ2 aS well as the unknown function g(·) are constructed. The asymptotic normality of β and σ2 is obtained. At the same time, the convergence rate of 3(·) is investigated. The results obtained in this paper are good as the corresponding ones for independent samples.