混合模型在医学研究中的应用与展望

Application of mixed models in medicine

医学研究中有很多资料都存在层次结构特征,而混合模型是处理该类数据的新兴的统计学方法。此文对混合模型(mixedmodels)的概念及其类型作了简要介绍,同时将混合模型与传统的固定效应模型进行比较,分析了国内外混合模型在医学研究中的应用现状,并对其前景作了展望。

Data in medical studies are often clustered. Mixed model is a statistical technique that extends ordinary regression analysis to the situation where the data are hierarchical. This article presents an overview of mixed model and its applications in medicine. And it will be my intention to try to dictate when mixed models should be used and to indicate the advantages of thinking about your problem as a mixed model. The distinguishing feature of mixed models compared with fixed effects models is that they are able to model data in which the observations are not independent.