多水平统计模型在Meta分析异质性控制中的作用  

Multi-Levels Statistical Model in the Heterogeneity Control of Meta-analysis

作　　者：仇瑶琴[1] 贺佳[2] 

机构地区：[1]第二军医大学护理系,上海200433 [2]第二军医大学卫生统计学教研室,上海200433

出　　处：《中国循证医学杂志》2011年第6期711-715,共5页Chinese Journal of Evidence-based Medicine

基　　金：国家科技重大专项(编号:2008ZX10002-018)

摘　　要：检索并综合国内外Meta分析异质性处理的相关文献,介绍基于随机效应的Meta回归、基线风险效应模型及基于分层贝叶斯的随机效应模型等多水平统计模型在Meta分析异质性控制中的应用。多水平统计模型将传统模型中单一的随机误差项分解到与数据层次结构相对应的水平上,其拟合效应不仅能使Meta分析结果更为稳健与合理,而且能通过对协变量的解释指导临床具体问题。Through collecting and synthesizing the paper concerning the method of dealing with heterogeneity in the meta analysis, to introduce the multi-levels statistical models, such as meta regression and baseline risk effect model based on random effects, and random effects model based on hierarchical bayes, and to introduce their application of con trolling the meta analysis heterogeneity. The multi-levels statistical model will decompose the single random error in the traditional model to data structure hierarchical. Its fitting effect can not only make the meta-analysis result more robust and reasonable, but also guide clinical issues through the interpretation of association variable.

关 键 词：多水平统计模型 META分析 异质性 控制 

分 类 号：R195[医药卫生—卫生统计学]