LMSMVE - A PROGRAM FOR LEAST MEDIAN OF SQUARES REGRESSION AND ROBUST DISTANCES

被引：11

作者：

DALLAL, GE

ROUSSEEUW, PJ

机构：

[1] UNIV INSTELLING ANTWERPEN,B-2650 EDEGEM,BELGIUM

[2] TUFTS UNIV,SCH NUTR,MEDFORD,MA 02155

来源：

COMPUTERS AND BIOMEDICAL RESEARCH | 1992年 / 25卷 / 04期

关键词：

D O I：

10.1016/0010-4809(92)90028-9

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The program LMSMVE performs robust regression analysis by using the method of the least median of squares. It also computes robust distances to locate leverage points, that is, outliers with respect to the set of independent variables. LMSMVE constructs plots of least median of squares residuals against robust distances. Both methods can tolerate up to half the data being outliers before they fail to give results that describe the bulk of the data. A complete system that operates directly on SYSTAT files is available for the IBM PC and compatibles; it includes a utility that converts ASCII files to SYSTAT format. © 1992.

引用

页码：384 / 391

页数：8

共 10 条

[1]

[Anonymous], 2003, ROBUST REGRESSION OU

[2]

DALLAL GE, 1987, AM STAT, V41, P328

[3]

Huber PJ., 1981, ROBUST STATISTICS

[4]

KIM SH, 1991, INT J VITAM NUTR RES, V61, P166

[5]

McLeod A, 1985, APPL STAT-J ROY ST C, V34, P198

[6] THE MINIMUM SUM OF ABSOLUTE ERRORS REGRESSION - A STATE OF THE ART SURVEY [J].

NARULA, SC ;

WELLINGTON, JF .

INTERNATIONAL STATISTICAL REVIEW, 1982, 50 (03) :317-326

[7]

Rousseeuw P., 1985, MATH STAT APPL, VB, P283

[8]

ROUSSEEUW PJ, 1990, J AM STAT ASSOC, V85, P633, DOI 10.2307/2289995

[9] LEAST MEDIAN OF SQUARES REGRESSION [J].

ROUSSEEUW, PJ .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1984, 79 (388) :871-880

[10]

WICHMANN BA, 1982, APPLIED STATISTICS, V31, P188

← 1 →