当方差未知时选取有最大均值总体的两阶段抽样方案(英文)  

A Two-Stage Procedure for Selecting the Population with the Largest Mean when Common Variance Is Unknown

作　　者：S.S.GUPTA 缪柏其[2] 孙东初[3] 

机构地区：[1]普度大学 [2]中国科技大学 [3]密苏里大学哥伦比亚分校

出　　处：《应用概率统计》1995年第2期113-127,共15页Chinese Journal of Applied Probability and Statistics

基　　金：国家自然科学基金资助项目

摘　　要：考虑k个有连续分布F_i=F(x-μ_i/δ)的总体,i=1,…,k。其中μ_i和δ均未知。我们通过两阶段抽取样本以得到最大均值的那个总体。第一步根据抽样删去一部分看来不可能的总体,第二步再从余下总体中抽样,取含样本均值最大的那个总体为所需总体。我们用渐近分布方法得到了在所定规则下能选到正确总体的概率下界,以及总抽样次数均值的上界。特别对Logistic总体计算了有关数值以及关于一次抽样的相对效。In this paper, the technique to select the population associated with the largest mean from k populations with unknown locations and a common unknown scale parameter is investigated. Asymptotic approximations to the distribution of the linear combination of the sample mean and the sample standard deviation has been derived. Using this approximation, an elimination type of two-stage procedure is proposed. Furthermore, two lower bounds on the probability of correct selection are obtained. This procedure are applied to the logistic population in detail.

关 键 词：最大均值 Logistic总体 总体 抽样方案 

分 类 号：O212.2[理学—概率论与数理统计]