正态模型下单边假设检验问题中频率与贝叶斯证据的一致性  

Consistency of the Frequentist and Bayesian Evidence in the One-Sided Testing Problems Under Normal Models

作　　者：尹玉良[1] 赵俊龙[2] 徐兴忠[1] 

机构地区：[1]北京理工大学理学院,北京100081 [2]北京航空航天大学数学与系统科学学院,数学、信息与行为教育部重点实验室,北京100191

出　　处：《北京理工大学学报》2011年第8期1001-1004,共4页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(11071015,11026049);国家教育部人文社科基金资助项目(10YJC910013)

摘　　要：假设检验问题中的频率与贝叶斯证据的一致性或和谐性是频率学派和贝叶斯学派所共同关心的问题.研究正态模型下单边假设检验问题中广义p-值以及Jeffreys无信息先验下的贝叶斯证据,证明了各种检验问题中两类证据的一致性.The agreement or reconcilability of the frequentist and Bayesian evidence in testing statistical hypotheses is commonly concerned by both the frequentist and the Bayesian school. For the one-sided hypothesis testing problem in the presence of nuisance parameters under normal distributions, the p-value and the Bayesian evidence against the null hypothesis were studied. It is shown that, for a variety of testing problems, these two kinds of evidence can reach an agreement.

关 键 词：先验分布 后验概率 广义P-值 讨厌参数 

分 类 号：O212[理学—概率论与数理统计]