A resistant estimator of multivariate location and dispersion

被引：25

作者：

Olive, DJ ^{[1
]}

机构：

[1] So Illinois Univ, Dept Math, Carbondale, IL 62901 USA

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2004年 / 46卷 / 01期

基金：

美国国家科学基金会;

关键词：

DD plot; minimum covariance determinant estimator;

D O I：

10.1016/S0167-9473(03)00119-1

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper presents a simple resistant estimator of multivariate location and dispersion. The DD plot is a plot of Mahalanobis distances from the classical estimator versus the distances from a resistant estimator and can be used to detect outliers and as a diagnostic for multivariate normality. The new estimator can be used in the DD plot, is easy to compute and provides insights about several useful robust algorithm techniques. (C) 2003 Elsevier B.V. All rights reserved.

引用

页码：93 / 102

页数：10

共 21 条

[1]

[Anonymous], 1987, ROBUST REGRESSION OU

[2] ASYMPTOTIC NORMALITY OF MULTIVARIATE TRIMMED MEANS [J].