THE ASYMPTOTIC-DISTRIBUTION OF THE RENYI MAXIMAL CORRELATION

被引：8
|
作者：
SETHURAMAN, J
机构：
[1] Department of Statistics, Florida State University, Tallahassee, FL
来源：
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 1990年 / 19卷 / 11期
关键词：
RENYI MAXIMAL CORRELATION; WISHART DISTRIBUTION; EIGENVALUES;
D O I：
10.1080/03610929008830442
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：
Renyi (1959) defined the maximal correlation rho between a pair of random variables (U, W) as sup {cov (f(U),g(W))/ square-root V(f(U))V(g(W)):V(f(U)) > 0, V(g(W)) > 0}, where the supremum is taken over all functions of U and W with finite second moments. In this paper we derive the asymptotic distribution of the estimate of the Renyi correlation coefficient based on a sample of independent observations under the assumption that (U, W) are independent and assume only a finite number of values.
引用
收藏
页码：4291 / 4298
页数：8
相关论文
共 50 条
12345