Characterizations of probability distributions via bivariate regression of generalized order statistics

被引:0
作者
Kotb, M. S. [1 ]
Ahsanullah, M. [2 ]
机构
[1] Al Azhar Univ, Fac Sci, Dept Math, Cairo 11884, Egypt
[2] Rider Univ, Dept Management Sci, Lawrenceville, NJ 08648 USA
来源
JOURNAL OF STATISTICAL THEORY AND APPLICATIONS | 2013年 / 12卷 / 04期
关键词
Generalized order statistics; Characterization; Regression function; Order statistics; Record values;
D O I
10.2991/jsta.2013.12.4.1
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
Let X-i,X-n,(m,k,) i = 1 ,..., n are n generalized order statistics (gos) based on an absolutely continuous distribution function F. Suppose that phi(x) is an absolutely continuous and monotonically increasing function in (a, b), - infinity <= a < b <= infinity, with finite phi(a(+)), phi(b(-)) and E(phi(X)). We give characterization of distributions based on the regression of linear combinations of gos. Using our results can obtain characterizations of some distributions.
引用
收藏
页码:321 / 329
页数:9
相关论文
共 17 条