基于排序集样本的最优挑选设计  

Optimal Selective Design Based on a Ranked Set Sample

作　　者：宋向东[1] 董晓芳[1] 

机构地区：[1]燕山大学理学院统计学系,河北秦皇岛066004

出　　处：《数理统计与管理》2007年第4期656-661,共6页Journal of Applied Statistics and Management

摘　　要：本文提出检验总体分位数的基于排序集挑选抽样的符号检验,分析了不同挑选设计相对于均衡设计的Pitman渐近效率。具体给出不同分位数的最优设计,并且最优设计不依赖于总体分布。Ranked set sample sign test under selective design is proposed for testing hypotheses concerning the quantile of a population characteristic. Both balance and selectiv designs are considered and the relative performance of different designs is assessde in terms of Pitman＇ s asymptotic relative efficiency. In particular, for each quantile, the design that maximizes the efficacy is identified and shown to not depend on the population distribution.

关 键 词：排序集抽样 挑选设计 效率 次序统计量 

分 类 号：O212.7[理学—概率论与数理统计]