Test of multivariate linear models using spatial concordances

被引：2
作者：
Choi, KM
Marden, JI
机构：
[1] Hongik Univ Jochiwon, Coll Sci & Technol, Dept Math, Jochiwon 339701, Yungi Chung Nam, South Korea
[2] Univ Illinois, Dept Stat, Champaign, IL 61820 USA
来源：
JOURNAL OF NONPARAMETRIC STATISTICS | 2005年 / 17卷 / 02期
关键词：
Kendall's tau; MANOVA; multivariate regression; Pitman efficiency;
D O I：
10.1080/1048525042000267761
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：
Kendall's tau for univariate samples is extended to the multivariate case using unit direction vectors in place of signs. Depending on whether the design matrix is fixed. this statistic yields a test for the multivariate analysis of variance or multivariate regression. Tests of independence based on this statistic are easy, efficient, and robust. Its asymptotic properties and its Pitman efficiency are studied. In addition, some useful algebra in multiple dimensions is presented.
引用
收藏
页码：167 / 185
页数：19
相关论文
共 17 条
[1]   High-breakdown rank regression [J].
Chang, WH ;
McKean, JW ;
Naranjo, JD ;
Sheather, SJ .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1999, 94 (445) :205-219
[2]   MULTIVARIATE LOCATION ESTIMATION USING EXTENSION OF R-ESTIMATES THROUGH U-STATISTICS TYPE APPROACH [J].
CHAUDHURI, P .
ANNALS OF STATISTICS, 1992, 20 (02) :897-916
[3]  
Chaudhuri P, 1996, J AM STAT ASSOC, V91, P862
[4]   An approach to multivariate rank tests in multivariate analysis of variance [J].
Choi, K ;
Marden, J .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (440) :1581-1590
[5]   A multivariate version of Kendall's τ [J].
Choi, K ;
Marden, J .
JOURNAL OF NONPARAMETRIC STATISTICS, 1998, 9 (03) :261-293
[6]   Multivariate analysis of variance using spatial ranks [J].
Choi, K ;
Marden, J .
SOCIOLOGICAL METHODS & RESEARCH, 2002, 30 (03) :341-366
[7]  
GAO Y, 2002, RANK BASED CORRELATI
[8]  
Gibbons J.D., 1985, NONPARAMETRIC STAT I
[9]   Nonparametric test of independence between two vectors [J].
Gieser, PW ;
Randles, RH .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (438) :561-567
[10]  
Johnson RA, 1998, J AM STAT ASSOC, V93, P807
12