Variable selection in joint frailty models of recurrent and terminal events |
| |
| Authors: | Dongxiao Han Xiaogang Su Liuquan Sun Zhou Zhang Lei Liu |
| |
| Institution: | 1. School of Statistics and Data Science & Key Laboratory of Pure Mathematics and Combinatorics, Nankai University, Tianjin, People's Republic of China;2. Department of Mathematical Sciences, University of Texas, El Paso, Texas;3. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, People's Republic of China;4. Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois;5. Division of Biostatistics, Washington University in St. Louis, St. Louis, Missouri |
| |
| Abstract: | Recurrent event data are commonly encountered in biomedical studies. In many situations, they are subject to an informative terminal event, for example, death. Joint modeling of recurrent and terminal events has attracted substantial recent research interests. On the other hand, there may exist a large number of covariates in such data. How to conduct variable selection for joint frailty proportional hazards models has become a challenge in practical data analysis. We tackle this issue on the basis of the “minimum approximated information criterion” method. The proposed method can be conveniently implemented in SAS Proc NLMIXED for commonly used frailty distributions. Its finite-sample behavior is evaluated through simulation studies. We apply the proposed method to model recurrent opportunistic diseases in the presence of death in an AIDS study. |
| |
| Keywords: | frailty models informative censoring proportional hazards models recurrent event survival analysis variable selection |
|
|
