New multicollinearity indicators in linear regression models

被引：31

作者：

Curto, Jose Dias ^{[1
]}

Pinto, Jose Castro ^{[1
]}

机构：

[1] ISCTE Business Sch, Dept Quantitat Methods, P-1600189 Lisbon, Portugal

来源：

INTERNATIONAL STATISTICAL REVIEW | 2007年 / 75卷 / 01期

关键词：

multiple linear regression; multicollinearity indicators; path analysis;

D O I：

10.1111/j.1751-5823.2007.00007.x

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：

Correlation is an important statistical issue for the Ordinary Least Squares estimates and for data-reduction techniques, such as the Factor and the Principal Components analyses. In this paper we propose new indicators for the multicollinearity problem in the multiple linear regression model.

引用

页码：114 / 121

页数：8

共 10 条

[1]

[Anonymous], ECONOMETRICS

[2]

Belsey D.A., 1980, Regression Diagnostics Identifying Influential Data and Sources of Collinearity

[3]

Dillon W.R., 1984, MULTIVARIATE ANAL ME

[4]

Greene W.H., 2000, ECONOMETRIC ANAL

[5]

Johnson RA., 2007, APPL MULTIVARIATE ST

[6]

Kovács P, 2005, INT STAT REV, V73, P405

[7]

MONTGOMERY D, 1999, HDB STAT METHODS ENG

[8]

MONTGOMERY DC, 1981, AIIE T, V13, P102, DOI 10.1080/05695558108974542

[9]

SENETA E, 1985, ENCY STATISTICAL SCI, V6, P635

[10] The problem of near-multicollinearity revisited: erratic vs systematic volatility [J].

Spanos, A ;

McGuirk, A .

JOURNAL OF ECONOMETRICS, 2002, 108 (02) :365-393

← 1 →