Estimators of the multiple correlation coefficient: local robustness and confidence intervals

被引:17
|
作者
Croux, C
Dehon, C
机构
[1] ECARES, Fac SOCO, B-1050 Brussels, Belgium
[2] Free Univ Brussels, Inst Stat, B-1050 Brussels, Belgium
关键词
influence function; multiple correlation coefficient; regression analysis; R-2-measure; robustness;
D O I
10.1007/s00362-003-0158-7
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
Many robust regression estimators are defined by minimizing a measure of spread of the residuals. An accompanying R-2-measure, or multiple correlation coefficient, is then easily obtained. In this paper, local robustness properties of these robust R-2-coefficients axe investigated. It is also shown how confidence intervals for the population multiple correlation coefficient can be constructed in the case of multivariate normality.
引用
收藏
页码:315 / 334
页数:20
相关论文
共 50 条