A RANDOM-SIZE SUBSET APPROACH TO THE SELECTION PROBLEM

被引:2
|
作者
LIU, W [1 ]
机构
[1] UNIV SOUTHAMPTON,DEPT MATH,SOUTHAMPTON SO17 1BJ,HANTS,ENGLAND
关键词
SUBSET SELECTION; INDIFFERENCE ZONE; MONOTONE LIKELIHOOD RATIO;
D O I
10.1016/0378-3758(94)00149-P
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 problem considered is to select the best population from among a finite number of populations. A new approach is proposed which is to select a random-size subset of populations that will contain the best population with a preassigned probability. This new approach is intuitively natural and needs no tables. For illustration, it is applied to four specific problems: the normal distribution with the largest mean, the normal distribution with the largest absolute value of mean, the Bernoulli distribution with the largest success probability, and the coin with the largest bias.
引用
收藏
页码:153 / 164
页数:12
相关论文
共 50 条