基于真假设比例广义推断的多重检验方法  

Multiple-Testing Procedure Based on Generalized Inference of True Null Hypotheses Proportion

作　　者：晋佩[1] 徐兴忠[1] 刘旭华[2] 

机构地区：[1]北京理工大学理学院,北京100081 [2]中国农业大学理学院,北京100193

出　　处：《北京理工大学学报》2011年第8期1005-1008,共4页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(11071015);中央高校基本科研业务费专项资金资助项目(15050110)

摘　　要：研究了多重假设检验方法的改进问题,基于真假设所占比例的广义推断,利用其广义置信上限对现有的多重假设检验方法进行改进.该方法更好地利用了水平,在功效上有很大提升.采用广义推断方法,即使在假设个数比较小时,也能对真假设所占比例做出较好推断.模拟结果表明,该方法显著提高了传统方法的功效.In this paper, modification of multiple testing procedure is considered. Based on the generalized inference of the number ratio of true null hypotheses to the total hypotheses, the confidence upper bound of that proportion can be used to modify the conventional multiple testing procedure. The proposed method exhausts the pre-specified level and is a great improvement over conventional one. Simulation results show that the proposed method has satisfying performance in multiple-testing procedure.

关 键 词：多重假设检验 广义推断 信仰推断 置信上限 

分 类 号：O212[理学—概率论与数理统计]