The generalised estimating equations: A comparison of procedures available in commercial statistical software packages

被引:0
|
作者
Ziegler, A
Gromping, U
机构
[1] Univ Marburg, Inst Med Biometry & Epidemiol, Med Ctr Methodol & Hlth Res, D-35033 Marburg, Germany
[2] Ford AG, Cologne, Germany
关键词
correlated data analysis; generalised linear model; longitudinal data analysis; marginal model;
D O I
10.1002/(SICI)1521-4036(199807)40:3<245::AID-BIMJ245>3.0.CO;2-N
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
The Generalised Estimating Equations (GEE) proposed by LIANG and ZEGER (1986) and ZEGER and LIANG (1986) have found considerable attention in the last decade (for an overview see e.g. ZIEGLER, KASTNER and BLETTNER, 1998). Several self-made programs for solving the GEE are available. This paper presents a comparison of three GEE procedures that are already available in SAS PROC GENMOD, STATA procedure XTGEE and SUDAAN PROC MULTILOG. We show that the estimation results may be quite distinct due to different implementations. Summing up, it is pleasant that GEE is becoming established in commercial software packages. However, some aspects of the implementations should be improved.
引用
收藏
页码:245 / 260
页数:16
相关论文
共 45 条