ROBUST-TYPE BIASED ESTIMATION IN GAUSS-MARKOV MODEL
ROBUST-TYPE BIASED ESTIMATION IN GAUSS-MARKOV MODEL
复制标题
高斯-马尔可夫模型中的鲁棒型有偏估计
DOI：
10.1179/sre.2005.38.298.299
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
Ou Ji
中科院分区：
文献类型：
--
作者：
Gui Qing;Li Guo;Ou Ji
摘要研究了多重共线性和离群点同时存在时的高斯-马尔可夫模型的参数估计问题。将稳健估计技术嫁接到哲学广义压缩估计中，提出了一类新的估计量--稳健型广义压缩估计。通过适当选择收缩参数矩阵，得到了许多有用和重要的估计，如稳健型普通岭估计、稳健型主成分估计等。建立了一种计算健壮型广义压缩估计的算法。数值算例表明，这些新的估计器不仅能有效地克服多重共线性带来的困难，而且能抵抗离群点的影响。
Abstract The parameter estimation problem in Gauss-Markov model is considered when multi-collinearity and outliers exist simultaneously. A class of new estimators, robust-type generalized shrunken estimators, is proposed by grafting robust estimation technique into philosophy generalized shrunken estimation. Many useful and important estimators such as robust-type ordinary ridge estimator, robust-type principal components estimator and so on are obtained by appropriate choices of the shrinking parameter matrix. An algorithm for computing the robust-type generalized shrunken estimate is established. A numerical example is provided to illustrate that these new estimators can not only effectively overcome difficulty caused by multi-collinearity but also resist the influence of outliers.
DOI：
10.1016/b978-0-12-386908-1.00037-9
发表时间：
2018-11
期刊：
Wiley Series in Probability and Statistics
影响因子：
--
作者：
Bruce E. Blaine
通讯作者：
Bruce E. Blaine