基于半参数Copula学习的确定性独立筛选研究  

Sure Independence Screening via Semiparameteric Copula Learning

作　　者：辛欣 谢博易 刘科科 XIN Xin;XIE Bo-yi;LIU Ke-ke(School of Mathematics and Statistics,Henan University,Kaifeng 475004,China)

机构地区：[1]School of Mathematics and Statistics,Henan University,Kaifeng 475004,China

出　　处：《Chinese Quarterly Journal of Mathematics》2024年第2期144-160,共17页数学季刊（英文版）

基　　金：Supported by Natural Science Foundation of Henan(Grant No.202300410066);Program for Science and Technology Development of Henan Province(Grant No.242102310350).

摘　　要：This paper is concerned with ultrahigh dimensional data analysis,which has become increasingly important in diverse scientific fields.We develop a sure independence screening procedure via the measure of conditional mean dependence based on Copula(CC-SIS,for short).The CC-SIS can be implemented as easily as the sure independence screening procedures which respectively based on the Pearson correlation,conditional mean and distance correlation(SIS,SIRS and DC-SIS,for short)and can significantly improve the performance of feature screening.We establish the sure screening property for the CC-SIS,and conduct simulations to examine its finite sample performance.Numerical comparison indicates that the CC-SIS performs better than the other two methods in various models.At last,we also illustrate the CC-SIS through a real data example.

关 键 词：Ultrahigh dimensionality Conditional mean dependence Copula learning Semiparametric method 

分 类 号：O212.1[理学—概率论与数理统计]