文章摘要
周舒冬,郜艳晖,李丽霞,张敏,杨翌,陈跃.稳健Poisson和log.binomial的GEE模型应用于非独立数据的研究[J].中华流行病学杂志,2014,35(4):449-452
稳健Poisson和log.binomial的GEE模型应用于非独立数据的研究
A simalation case study under the use of robust Poisson and log.binomial model with generalized estimating equation models regarding non-independent data
收稿日期:2013-10-18  出版日期:2015-04-27
DOI:10.3760/cma.j.issn.0254-6450.2014.04.024
中文关键词: 稳健Poisson回归;log.binomial模型;非独立;广义估计方程
英文关键词: Robust Poisson regression;Log-binomial model;Non-independent;Generalized estimating equation
基金项目:广东省自然科学基金(10151022401000018)
作者单位E-mail
周舒冬 广东药学院公共卫生学院流行病与卫生统计学系广东省分子流行病学重点实验室, 广州 510310  
郜艳晖 广东药学院公共卫生学院流行病与卫生统计学系广东省分子流行病学重点实验室, 广州 510310 gao_yanhui@.163.com 
李丽霞 广东药学院公共卫生学院流行病与卫生统计学系广东省分子流行病学重点实验室, 广州 510310  
张敏 广东药学院公共卫生学院流行病与卫生统计学系广东省分子流行病学重点实验室, 广州 510310  
杨翌 广东药学院公共卫生学院流行病与卫生统计学系广东省分子流行病学重点实验室, 广州 510310  
陈跃 加拿大渥太华大学流行病与社区医学系  
摘要点击次数: 1108
全文下载次数: 914
中文摘要:
      探讨流行病学资料中非独立数据的RR/患病率比(PR)的合适估计方法 。采用计算机模拟实验和实例分析观察稳健Poisson.GEE和log-binomial.GEE模型的适用性并进行比较。结果 表明log.binomial-GEE模型与稳健Poisson-GEE模型的收敛率基本均为100%,两模型估计各参数的平均值均与真值接近;在类内聚集性变小或类别数增加时,两模型估计各参数的95%CI覆盖率均有所提高;稳健Poisson.GEE模型对参数估计的稳健性较好,应用到实例时可正确评价暴露对结局的影响。稳健Poisson和log.binomial的GEE模型很少存在收敛问题,且有较高的准确率,可用于流行病学资料中非独立数据的RR/PR值估计。
英文摘要:
      To explore the appropriate method in estimating relative risk(RR)/prevalence ratio(PR)related to non·independent datasets.The simulation datasets generated by computer and case study were analyzed by two generalized estimating equation(GEE)models to investigate and compare the related applicability.Both convergence effects of log·binomial·-GEE model and Robust Poisson.GEE model were almost 100%.The estimation Results of the two GEE models were both closer to the true value.95%Cl coverage of the two GEE models increased along with the reduction of class aggregation or the increase of the number of categories.Robust-Poisson-GEE model seemed to be more stable and steady than the log-binomial-GEE.The two GEE models could correctly evaluate the effects of exposure on the outcome in the case study.Rarely,there appeared problems on convergence of Robust Poisson or log-binomial-GEE model,and the accuracy was high.Both models could be used to estimate the RRiPR on non-independent epidemiological data.
查看全文   Html全文     查看/发表评论  下载PDF阅读器
关闭