基于有金标准下的部分核实数据对疾病流行率的齐性检验  

Homogeneity Test of Disease Prevalence Under the Gold Standard Based on Partially Validated Series

作　　者：刘多伟 邱世芳 何杰 LIU Duowei;QIU Shifang;HE Jie(College of Science,Chongqing University of Technology,Chongqing 400054,China)

机构地区：[1]重庆理工大学理学院

出　　处：《重庆理工大学学报（自然科学）》2019年第5期192-201,共10页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(11471060,11871124);国家统计局统计科研重点项目(2017LZ27)

摘　　要：考虑了基于有金标准核实检验下的分层部分核实数据对疾病流行率的齐性检验问题,提出了加权最小二乘统计量、加权最小二乘统计量的对数变换、基于对数变换、logit变换和双对数变换的加权最小二乘统计量、Score和似然比检验统计量的检验过程,并通过蒙特卡罗随机模拟研究了各种检验的统计性质。模拟结果表明:基于Score统计量和似然比统计量的检验能很好地控制犯第一类错误的概率且具有较高的功效,因而被强烈推荐到实际应用中。实际数据分析进一步验证了本文所提方法的有效性。This paper considers the homogeneity test of the disease prevalence rate based on partially validated series of the stratified under the gold standard verification test,and proposes the weighted least squares statistic,the logarithmic transformation of the weighted least squares statistic,weighted least squares statistic based on logarithmic transformation,logit transformation and double logarithmic transformation,Score and likelihood ratio statistic,and the statistical properties of various tests were studied by Monte Carlo stochastic simulation.The simulation results show that the test based on Score statistic and likelihood ratio statistic can control the probability of making the type I error rate well and has high power,so it is strongly recommended to practical application.The actual data analysis further validates the effectiveness of the proposed methods.

关 键 词：部分核实数据 分层设计 齐性检验 Score统计量 似然比统计量 

分 类 号：O212.1[理学—概率论与数理统计]