ON NONLINEAR RANDOM EFFECTS MODELS FOR REPEATED MEASUREMENTS

被引:37
|
作者
HIRST, K [1 ]
BOYLE, DW [1 ]
ZERBE, GO [1 ]
WILKENING, RB [1 ]
机构
[1] UNIV COLORADO,SCH MED,DENVER,CO 80206
基金
美国国家卫生研究院;
关键词
NONLINEAR MIXED EFFECTS MODEL; EM ALGORITHM; LONGITUDINAL DATA; STOCHASTIC PARAMETERS;
D O I
10.1080/03610919108812966
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Linear random effects models for longitudinal data discussed by Laird and Ware (1982), Jennrich and Schluchter (1986), Lange and Laird (1989), and others are extended in a straight forward manner to nonlinear random effects models. This results in a simple computational approach which accommodates patterned covariance matrices and data insufficient for fitting each subject separately. The technique is demonstrated with an interesting medical data set, and a short, simple SAS PROC IML program based on the EM algorithm is presented.
引用
收藏
页码:463 / 478
页数:16
相关论文
共 50 条