基于局部多项式方法的异方差估计  

A Heteroscedasticity Estimation Based on Local Polynomial Method

作　　者：张晓琴 郭雅静 米子川[1] ZHANG Xiao-qin;GUO Ya-jing;MI Zi-chuan(School of Statistics,Shanxi University of Finance and Economics,Taiyuan 030006,China;School of Sciences,Hebei University of Architecture,Zhangjiakou 075024,China)

机构地区：[1]山西财经大学统计学院,山西太原030006 [2]河北建筑工程学院数理系,河北张家口075024

出　　处：《数理统计与管理》2021年第6期1019-1030,共12页Journal of Applied Statistics and Management

基　　金：国家社科基金一般项目(17BTJ010);山西省基础研究计划项目(201901D111320);山西省留学回国人员科技活动择优资助项目(2019-13).

摘　　要：解决异方差问题的关键是对随机误差项的方差做出有效性估计.一般地,异方差分布形式未知时,非参数估计的效果较好.因此,本文在异方差模型的估计中引入了局部多项式的非参数方法,提出了一种新的异方差估计方法.同时,通过计算机模拟实验和城市流动人口实地调查的案例分析将本文提出的方法与已有的异方差估计方法进行了比对,并进行了有效性验证.The key to solve the heteroscedastic problem is to estimate reasonably the variance of the random error term.When the heteroscedasticity distribution is unknown,nonparametric estimation is generally considered to be effective.Therefore,in this paper,the nonparametric method of local polynomial is introduced to estimate the heteroscedasticity model,and a new heteroscedasticity estimation method is proposed.At the same time,the comparison between the method proposed in this paper and the existed heteroscedasticity estimation method is carried out through computer simulation experiment and case analysis of the field survey of urban floating population,which proves the effectiveness of the method.

关 键 词：异方差 局部多项式估计 HCCMEs 协方差阵 

分 类 号：F272[经济管理—企业管理] O212[经济管理—国民经济]