摘要
基于相对危险度提出了一个新的假设检验问题,并就此检验问题,在配对设计下用delta方法构建了对数变换检验统计量,运用Monte Carlo方法模拟显示对数变换检验统计量有优良的统计性能,表现在它的经验第一类错误率与给定的显著性水平很接近,是理想检验.
A new test hypothesis is proposed in this paper. Delta is adopted to derive the logarithmic transformation test statistic of relative risk for matched - pair design. It is shown through the simulation by Monte Carlo method that this hypothesis is an ideal test ,which enjoys a good statistic performance because its empirical type I error rates are generally much closer to the assumed nominal level.
出处
《昆明理工大学学报（理工版）》
北大核心
2009年第5期116-120,共5页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
云南大学理(工)科校级科研项目资助(项目编号:2008YB025)
云南省教育厅科学研究基金项目(项目编号:07L00001)
关键词
配对设计
相对危险度
对数变换检验
matched -pair design
relative risk
logarithmic transformation test
