METHODS OF L1 ESTIMATION OF A COVARIANCE-MATRIX
METHODS OF L1 ESTIMATION OF A COVARIANCE-MATRIX
复制标题
DOI：
10.1016/0167-9473(87)90054-5
复制
发表时间：
1987-09-01
影响因子：
1.8
通讯作者：
HAWKINS, DM
中科院分区：
文献类型：
--
作者：
GALPIN, JS;HAWKINS, DM
利用协方差矩阵的谱分解及其主成分估计之间的经典关系，基于L1公式，从主成分的稳健估计中获得稳健协方差矩阵估计.这些估计的性能进行了研究，使用一些有问题的数据集在文献中讨论。
The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on L 1 formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.