摘要
探讨了现代统计学的重要模型:广义线性混合模型.该模型的用途极为广泛,例如可用于临床学中的纵向数据分析及流行病和农业中的空间数据分析.讨论了该模型中参数的估计方法.并用统计软件R展示了怎样用广义线性混合模型去分析实际数据.其演示表明广义线性混合模型是一种处理非正态、非线性相关数据的有力工具.
One of the advanced statistical models is studied： Generalized Linear Mixed Models （GLMM）. The use of the GLMM is much wider, from longitudinal/clustered data modeling encountered commonly in randomized clinical trials to spatial data modeling arising often in epidemiology and agriculture. The estimation procedure for obtaining the penalized quasi - likelihood of fixed effects and variance components in the GLMM is presented. The use of the function GLMMPQL（ ） in the statistical package R is demonstrated through analyzing a real data set arising in a clinical trial. It is concluded that the GLMM is a powerful statistical model for modeling clustered non - Normal and non - linear data.
出处
《昆明理工大学学报（理工版）》
2007年第4期107-113,共7页
Journal of Kunming University of Science and Technology(Natural Science Edition)
关键词
固定效应
线性混合模型
方差分量
fixed effects
generalized linear mixed models
variance components
