混合模型及其在药理研究中的应用

Mixed Model and Its Application to the Research of Pharmacology

目的：减少人们误用统计学的机会，使药理学研究中定量资料的统计处理更加科学；方法：揭示药理学研究中一种最常见的实验设计类型及其资料的特点，指出许多医学期刊中常用ｔ检验和一般方差分析处理这种资料的错误，并给出正确的统计分析方法；结果：展示了混合模型在分析复杂数据结构中的特殊作用；结论：一般线性模型在处理含随机效应的数据时存在困难。

Objective To reduce the chance of misusing statistics and to make more scientific researchers'analysis of the quantitative data in the research of pharmacology. Methods A most common type of experiment design and the characteristics of its data were revealed.The t test and conventional analysis of varance were often misused for analyzing the data in many medical journals and the correct methods of statistical analysis were given in this paper.Results:The special functions of the mixed model in analyzing the complicated data structure were presented.Conclusion:It is difficult to take into account the data including random effect by a general linear model,whereas the mixed model,very flexible and effective,can deal with the difficulties successfully.