Variable selection in joint modelling of mean and covariance structures for longitudinal data

科研成果详情

题名	Variable selection in joint modelling of mean and covariance structures for longitudinal data
作者	Kou, Chaofeng; Pan, Jianxin
发表日期	2008
会议名称	23rd International Workshop on Statistical Modelling, Utrecht, 2008
会议录名称	Proceedings of the 23rd International Workshop on Statistical Modelling. Utrecht, 7-11 July 2008
页码	305-310
会议日期	7-11 July 2008
会议地点	Utrecht
摘要	Joint modelling of mean-covariance structures is important in longitudinal studies. Correct modelling of covariance structures improves the efficacy of statistical inferences. Like the mean structure, covariances may depend on various explanatory variables of interest. We thus propose a new approach, based on penalty methods including LASSO, HARD thresholding and SCAD techniques, to select the most important explanatory variables that affect the modelling of mean and covariances structures for longitudinal data.
关键词	Variable selection Cholesky decomposition Joint modeling Penal ized maximum likelihood
URL	查看来源
语种	英语English
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/8405
专题	个人在本单位外知识产出
作者单位	School of Mathematics, The University of Manchester, Manchester, M13 9PL
推荐引用方式 GB/T 7714	Kou, Chaofeng,Pan, Jianxin. Variable selection in joint modelling of mean and covariance structures for longitudinal data[C], 2008: 305-310.