在函数逼近论观点下半参数变系数非线性回归函数的估计  

Estimation for semi-parametric varying coefficient non-linear regression function under the viewpoint of functional approximation

作　　者：陈乃辉[1] 

机构地区：[1]中央财经大学应用数学学院,北京100081

出　　处：《纯粹数学与应用数学》2010年第2期220-230,共11页Pure and Applied Mathematics

摘　　要：在函数逼近论的观点下研究了半参数变系数非线性回归函数的估计问题.采用总体之下L2多项式最佳逼近的方法与样本之下矩估计的方法,独立地分别作出非参数部分与变系数参数部分的解析函数形式的估计,最终得到回归函数的L2与强相合之联合收敛意义下的估计.By the viewpoint of functional approximation the estimation for semi-parametric varying coefficient non-linear regression function is studied.The methods of L2 best approximation of polynomial and moment estimation are used to estimate independently non-parametric part and varying coefficient parametric part,in this way the estimation of regression function is obtained and it converge to regression function under the joint meaning of L2 convergence and strong consistent.

关 键 词：半参数变系数回归函数 L2收敛 矩估计 强相合性 

分 类 号：O212.1[理学—概率论与数理统计]