Econometric applications of high-breakdown robust regression techniques

被引：81

作者：

Zaman, A

Rousseeuw, PJ

Orhan, R ^{[1
]}

机构：

[1] Fatih Univ, Dept Econ & Comp Sci, Istanbul, Turkey

[2] Lahore Univ Management Sci, Lahore, Pakistan

[3] Univ Instelling Antwerp, Dept Math & Comp Sci, Antwerp, Belgium

来源：

ECONOMICS LETTERS | 2001年 / 71卷 / 01期

关键词：

high breakdown estimates; masking; robust regression; outlier; leverage point; least trimmed squares (LTS); minimum covariance determinant (MCD);

D O I：

10.1016/S0165-1765(00)00404-3

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

A literature search shows that robust regression techniques are rarely used in applied econometrics. We present a technique based on Rousseeuw and Van Zomeren [Journal of the American Statistical Association, 85 (1990) 633-639] that removes many of the difficulties in applying such techniques to economic data. We demonstrate the value of these techniques by re-analyzing three OLS-based regressions from the literature. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：1 / 8

页数：8

共 15 条

[1]

BELSLEY D. A, 1980, Wiley Series in Probability and Mathematical Statistics

[2]

BENDERLY J, 1985, AM ECON REV, V75, P1115

[3]

DELONG JB, 1991, Q J ECON, V106, P445

[4] On the robustness of size and book-to-market in cross-sectional regressions [J].