序集抽样中M估计分布的随机加权逼近  

APPROXIMATION TO THE DISTRIBUTION OF M-ESTIMATES IN RANKED-SET SAMPLING BY RANDOMLY WEIGHTED BOOTSTRAP

作　　者：吴耀华[1] 刘驰宇[1] 

机构地区：[1]中国科学技术大学统计与金融系,合肥230026

出　　处：《系统科学与数学》2009年第5期693-705,共13页Journal of Systems Science and Mathematical Sciences

基　　金：国家自然科学基金(10871188);中国科学院知识创新工程(KJCX3-SYW-S02)资助课题

摘　　要：序集抽样是一种适用于准确测量花费太高而排序费用可以忽略不记时的一种抽样方法.讨论了序集抽样下的对于一般分布族M估计的相合性和渐近正态性并且通过随机加权的方法来估计M估计的分布.Ranked-Set Sampling（RSS） is a sampling method when a set of sampling units drawn from the population can be ranked by certain means rather cheaply without the actual measurement of the variable of interest which is costly and/or time consuming. This paper is concerned with the consistency and asymptotic normality on the RSS M-estimates and approximation to its distribution by randomly weighted bootstrap.

关 键 词：序集抽样 M估计 随机加权 渐近正态性 

分 类 号：O212.2[理学—概率论与数理统计]