| 摘要: |
| 本文研究了发散维数SICA惩罚Cox回归模型的调节参数选择问题，提出了一种修正的BIC调节参数选择器.在一定的正则条件下，证明了方法的模型选择相合性.数值结果表明提出的方法表现要优于GCV准则. |
| 关键词: Cox模型 修正BIC 惩罚似然 SICA惩罚 光滑拟牛顿 |
| DOI： |
| 分类号:O212.1 |
| 基金项目:Supported by National Natural Science Foundation of China (11501579); Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan) (CUGW150809). |
|
| A MODIFIED BIC TUNING PARAMETER SELECTOR FOR SICA-PENALIZED COX REGRESSION MODELS WITH DIVERGING DIMENSIONALITY |
|
SHI Yue-yong1,2, JIAO Yu-ling3, YAN Liang1, CAO Yong-xiu3
|
|
1.School of Economics and Management, China University of Geosciences, Wuhan 430074, China;2.Center for Resources and Environmental Economic Research, China University of Geosciences, Wuhan 430074, China;3.School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan 430073, China
|
| Abstract: |
| This paper proposes a modifled BIC (Bayesian information criterion) tuning parameter selector for SICA-penalized Cox regression models with a diverging number of covariates. Under some regularity conditions, we prove the model selection consistency of the proposed method. Numerical results show that the proposed method performs better than the GCV (generalized crossvalidation) criterion. |
| Key words: Cox models modifled BIC penalized likelihood SICA penalty smoothing quasi-Newton |
