INTERIOR ANALYSIS FOR THE MINIMUM SUM OF ABSOLUTE ERRORS REGRESSION

被引：17

作者：

NARULA, SC ^{[1
]}

WELLINGTON, JF ^{[1
]}

机构：

[1] GANNON UNIV, ERIE, PA 16541 USA

来源：

TECHNOMETRICS | 1985年 / 27卷 / 02期

关键词：

MATHEMATICAL PROGRAMMING; LINEAR;

D O I：

10.2307/1268766

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

The authors study the effect of each observation in a data set on the minimum sum of absolute errors (MSAE) regression. First, the authors study the extent to which the value of a response variable for an observation can be changed without affecting the MSAE regression fit and then show that MSAE regression is less sensitive to certain types of discrepant observations. Second, the authors study the effect of deleting an observation on parameter estimation.

引用

页码：181 / 188

页数：8

共 22 条

[1] ROBUST METHOD FOR MULTIPLE LINEAR-REGRESSION [J].

ANDREWS, DF .

TECHNOMETRICS, 1974, 16 (04) :523-531

[2] IMPROVED ALGORITHM FOR DISCRETE L1 LINEAR-APPROXIMATION [J].

BARRODALE, I ;

ROBERTS, FDK .

SIAM JOURNAL ON NUMERICAL ANALYSIS, 1973, 10 (05) :839-848

[3]

BARRODALE I, 1968, APPLIED STATIST, V17, P51

[4]

BASKERVILLE JC, 1982, TECHNOMETRICS, V24, P9

[5]

BECKMAN RJ, 1983, TECHNOMETRICS, V25, P119, DOI 10.2307/1268541

[6]

BROWNLEE KA, 1965, STATISTICAL THEORY M

[7]

COOK RD, 1980, TECHNOMETRICS, V22, P495

[8]

Daniel C., 1980, FITTING EQUATIONS DA

[9] 2 DIAGNOSTIC DISPLAYS FOR ROBUST REGRESSION-ANALYSIS [J].

DENBY, L ;

MALLOWS, CL .

TECHNOMETRICS, 1977, 19 (01) :1-13

[10]

Dielman T., 1982, TIMS STUDIES MANAGEM, P31

← 1 2 3 →