摘要
为同时克服线性回归模型的自相关性和回归变量间的复共线性,通过融合主成分回归估计和s-K估计,提出一类新估计,称为主成分s-K估计;并在均方误差阵意义下,得到了这类估计分别优于广义最小二乘估计、主成分估计、r-k和s-K估计的充要条件.Monto Carlo数值模拟表明,新估计是一种同时克服自相关性和复共线性的有效方法.
To combat autocorrelation in errors and multicollinearity among the regressors in linear regression model,we proposed a new estimator by combining the principal components regression(PCR)estimator and the s-Kestimator.Then necessary and sufficient conditions for the superiority of the new estimator over the GLS,the PCR,the r-k and the s-K estimators were derived by the mean squared error matrix criterion.Finally,a Monte Carlo simulation study was carried out to investigate the performance of the proposed estimator.
出处
《吉林大学学报(理学版)》
CAS
CSCD
北大核心
2015年第3期444-450,共7页
Journal of Jilin University:Science Edition
基金
安徽省自然科学基金(批准号:1308085QA13)
关键词
自相关性
复共线性
主成分回归估计
s-K估计
均方误差阵
autocorrelation
multicollinearity
principal components regression estimator
s-K estimator
mean squared error matrix