Grouped Penalization Estimation of the Osteoporosis Data in the Traditional Chinese Medicine
Both continuous and categorical covariates are common in Traditional Chinese Medicine (TCM) research, especially in the clinical symptoms identification and the risk prediction research. For groups of dummy variables which are generated by the same categorical covariate, it is important to penalize them groupwise rather than individually. In this paper, we discuss the group lasso method for a risk prediction analysis in TCM osteoporosis research. It is the first time to apply such a group-wise variable selection method in this field. It may lead to new insights of using the grouped penalization method to select appropriate covariates in the TCM research. The introduced methodology can select categorical and continuous variables, and estimate their parameters simultaneously. In our analysis for the osteoporosis data, four covariates (both categorical and continuous covariates) are selected out of fifty-two covariates. The accuracy of the prediction model is excellent. Compared with the prediction model with different covariates, the group lasso risk prediction model can significantly decrease the error-rate and make it easy for TCM doctors to identify the high risk population with osteoporosis in clinical practice. Simulation results show that the application of the group lasso method is reasonable for the categorical covariates selection model in this TCM osteoporosis research.
Variable Selection CategoricalCovariates Group Lasso Traditional Chinese Medicine Osteoporosis
Yang Li Yichen Qin Yanming Xie Feng Tian
School of Statistics,Renmin University of China,Beijing,P.R.China,100872 Center for Applied Statisti Department of Applied Mathematics and Statistics,Johns Hopkins University,Baltimore,MO,U.S.A.,21218 Institute of Basic Research in Clinical Medicine,China Academy of Chinese Medicine Science,Beijing,P
国际会议
Second Joint Biostatistics Symposium(第二届生物统计国际研讨会2012)
北京
英文
506-521
2012-07-08（万方平台首次上网日期，不代表论文的发表时间）