有结构变化的半参数回归模型及其级数估计  

A Semiparametric Regression Model with Structural Change and its Series Estimator

作　　者：王成勇[1] 艾春荣[2] 

机构地区：[1]襄樊学院数学与计算机科学学院,湖北襄樊441053 [2]上海财经大学统计与管理学院,上海200433

出　　处：《应用数学》2010年第2期261-266,共6页Mathematica Applicata

基　　金：湖北省教育厅科研项目(B200725002);湖北省社科基金项目(20099133)

摘　　要：结合半参数回归模型和含未知变点的结构变化模型,提出一个参数和非参数分量同时存在结构变化的新模型——有结构变化的半参数回归模型.在新模型非参数分量的级数估计基础上,得出模型参数的最小二乘估计,进一步推得条件期望函数估计的收敛速度及其渐近正态性.随机模拟结果表明,本文的新模型及估计方法具有广泛的适用性和灵活性.Combined with semiparametric regression model and structural change model with unknown change point,a new regression model with structural change both in parametric and nonparametric component——semiparametric regression model with structural change has been established.In new model,based on the series estimator of nonparametric components,the OLS estimator of model＇s parameters are given.And then,convergence rates and asymptotic normality of the estimator of conditional expectation function are conducted.The simulation results show that,our new model and estimation method are more flexible and have comprehensive applicability.

关 键 词：半参数回归模型 含未知变点的结构变化模型 级数估计 收敛速度 渐近正态性 

分 类 号：O212.1[理学—概率论与数理统计]