THE FINITE-SAMPLE BREAKDOWN POINT OF THE OJA BIVARIATE MEDIAN AND OF THE CORRESPONDING HALF-SAMPLES VERSION

被引：31
作者：
NIINIMAA, A [1 ]
OJA, H [1 ]
TABLEMAN, M [1 ]
机构：
[1] RUTGERS STATE UNIV,DEPT STAT,NEW BRUNSWICK,NJ 08903
来源：
STATISTICS & PROBABILITY LETTERS | 1990年 / 10卷 / 04期
关键词：
D O I：
10.1016/0167-7152(90)90050-H
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 purpose of this note is twofold. First it is shown that the finite-sample breakdown point of the bivariate median proposed by Oja (1983) is 2/(n + 2) which tends to zero rather than the previously conjectured 1 3. Then second, it is shown that applying a very general half-samples approach to the Oja criterion function leads to a class of estimators enjoying the 50% breakdown property and containing, as a special case, Rousseeuw's (1985, 1987) minimum covariance determinant estimator. © 1990.
引用
收藏
页码：325 / 328
页数：4
相关论文
共 10 条
[1]  
[Anonymous], 2003, ROBUST REGRESSION OU
[2]  
BROWN BM, 1989, J ROY STAT SOC B MET, V51, P117
[3]  
BROWN BM, 1987, J ROY STAT SOC B MET, V49, P301
[4]  
BROWN BM, 1983, J ROY STAT SOC B MET, V45, P25
[5]  
DONOHO DL, 1982, THESIS HARVARD U CAM
[6]  
LOPUHAA HP, 1987, 14 DELFT U TECH FAC
[7]  
OJA H, 1985, J ROY STAT SOC B MET, V47, P372
[8]  
Oja H., 1983, STATISTICS PROBABILI, V1, P327, DOI [DOI 10.1016/0167-7152(83)90054-8, 10.1016/0167-7152(83)90054-8]
[9]  
Rousseeuw P., 1985, MATH STAT APPL, VB, P283
[10]  
Wilks S.S., 1960, CONTRIB PROBAB STAT, P486
1