Categorical Predictor Selection of the Osteoporosis in Traditional Chinese Medicine Research by the Group Lasso

摘要：

Traditional Chinese Medicine(TCM)study typically has both continuous and categorical covariates,especially for the clinical TCM symptoms identification and risk prediction in variable selection models.Previous research has shown that it is important to penalize dummy variables group-wisely rather than individually,because each group of dummy variables is generated by the same categorical covariate.

关键词： Variable Selection Categorical Covariates Group Lasso Osteoporosis

作者: Y Li Y Qin D Yi Y Xie B Shia S Ma

作者单位: School of Statistics,Renmin University of China,Beijing,P.R.China,100872;School of Public Health,Yal Department of Applied Mathematics and Statistics,Johns Hopkins University,Baltimore,MD,U.S.A.,21218 School of Statistics,Renmin University of China,Beijing,P.R.China,100872 Institute of Basic Research in Clinical Medicine,China Academy of Chinese Medicine Science,Beijing,P Department of Statistics and Information Science,Fu Jen Catholic University,Taipei,24205 School of Public Health,Yale University,New Haven,CT,U.S.A.,06511

会议类型: 国内会议

会议名称: 第四届临床评价方法与应用国际研讨会(2011)

会议地点: 北京

会议语种:英文

页码: 1-1

在线出版日期: 2011-07-02（万方平台首次上网日期，不代表论文的发表时间）