DISTRIBUTIONAL CONVERGENCE OF M-ESTIMATORS UNDER UNUSUAL RATES

被引：7
|
作者：
ARCONES, MA [1 ]
机构：
[1] UNIV UTAH,DEPT MATH,SALT LAKE CITY,UT 84112
来源：
STATISTICS & PROBABILITY LETTERS | 1994年 / 21卷 / 04期
基金：
美国国家科学基金会;
关键词：
M-ESTIMATOR; EMPIRICAL PROCESS; RATE OF CONVERGENCE; LP-MEDIAN;
D O I：
10.1016/0167-7152(94)00013-1
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：
Usually the rate of convergence of M-estimators is n1/2. Kim and Pollard (1990) showed that several estimators have a rate of convergence n1/3. Here, we will see that other rates are also possible. This is applied to the study of the convergence of the L(p)-medians for 0 < p less-than-or-equal-to 1/2.
引用
收藏
页码：271 / 280
页数：10
相关论文
共 50 条
12345