纵向观测二分类数据的广义线性模型分析

Analysis of longitudinal binary data using generalized linear models

目的：利用广义线性模型对纵向观测二分类数据进行分析，充分考虑纵向观测间的相关性，给出一般分析方法。方法：采用Ｚｅｇｅｒ和提出的广义估计方程，拟合ｌｏｇｉｓｔｉｃ广义线性模型，讨论３种协方差矩阵结构。结果：同时获得回归参数、相关参数的估计，完成了较为实用的运行程序，并进行了实例分析。结论：医学研究和临床试验中经常接触到纵向观测数据，对这类数据需采用特殊的方法进行分析处理，以解决重复观测间的相关性问题。

Objective: To analyze longitudinal binary data by using generalized linear models. with consideration of the correlation between repeated measures. Methods: Generalized estimating equations (GEE) proposed by Zeger and Liang was used. For several covariance structures, one method was given for estimating regression and correlation parameters. Results: Regression and correlation parameters were estimated simultaneously. A set of program was finished and an example was illustrated. Conclusion: Longitudinal data often occur in medical researches and clinical trials. To solve the problem of correlation between repeated measures, it is necessary to use some special methods to cope with this kind of data.