带有约束的部分线性变系数EV模型的偏差纠正统计推断  

Bias-corrected Statistical Inference for Restricted Partially Linear Varying Coefficient Errors-in-variables Models

作　　者：樊明智[1] 胡玉萍[2] 

机构地区：[1]许昌学院数学与统计学院,河南许昌461000 [2]郑州大学数学与统计学院,河南郑州450052

出　　处：《应用数学》2015年第4期715-722,共8页Mathematica Applicata

基　　金：河南省科技攻关项目(082102210091);全国统计科学研究重点项目(2014LZ45)

摘　　要：本文研究参数和非参数部分均带有测量误差(EV)的部分线性变系数模型的约束统计推断,综合profile最小二乘估计方法和局部纠偏方法给出模型中未知参数和系数函数的两种约束估计,并在适当条件下证明它们的渐近性质.最后通过数值模拟研究所提估计方法在有限样本下的实际表现.In this paper, we consider the statistical inference for the partially liner varying coefficient model when the covariates in the parametric and nonparametric parts are all measured with errors and some additional linear restrictions on the parametric component are available. Two types of bias-corrected restricted profile least squares estimators of the parametric component and nonparametric component are conducted, and their asymptotic properties are also studied under some regularity conditions. A simulation study is conducted to examine the finite sample performance for the proposed method.

关 键 词：部分线性变系数模型 测量误差 约束估计 profile最小二乘 渐近正态性 

分 类 号：O212.7[理学—概率论与数理统计]