基于区间数据的非参数Bayes估计  

Nonparametric Bayesian Estimation Based on Interval Censored Data

作　　者：周丽萍[1] 程建强[1] 何幼桦[1] 

机构地区：[1]上海大学理学院,上海200444

出　　处：《上海大学学报（自然科学版）》2010年第3期290-296,共7页Journal of Shanghai University:Natural Science Edition

基　　金：国家自然科学基金资助项目(60773081);上海市重点学科建设资助项目(S30104)

摘　　要：基于Dirichlet过程为先验分布,给出区间数据下总体分布非参数Bayes估计的表达式;通过对常用分布的随机模拟,阐述几类先验分布对估计效果的影响;最后,与参数极大似然法比较,证明所构造的方法具有相近的估计效果.The nonparametric Bayesian estimation of population distribution with interval censored data based on Dirichlet process as a prior distribution is gived.By random simulation for some common distributions,the effects of some prior distributions on the estimated results are discussed.Comparison between the proposed method and the parametric maximum likelihood method shows similar estimation effects.

关 键 词：Dirichlet过程 区间数据 BAYES估计 非参数估计 

分 类 号：O212[理学—概率论与数理统计]