删失回归模型中的变量选择(英文)  

Variable Selection for Censored Regression Models

作　　者：金曼[1] 方易新[1] 赵林城[1] 

机构地区：[1]中国科学技术大学统计与金融系,合肥230026

出　　处：《应用概率统计》2005年第2期141-149,共9页Chinese Journal of Applied Probability and Statistics

基　　金：Research partially supported by National Natural Science Foundation of China (Grant No. 10471136) Ph.D. Program Foundation of the Ministry of Education of China, and Special Foundations of the Chinese Academy of Science and USTC.

摘　　要：在一个删失回归模型("Tobit"模型)中,我们常常要研究如何选择重要的预报变量.本文提出了基于信息理论准则的两种变量选择程序,并建立了它们的相合性.In many situations, we are interested in selection of important variables which are adequate for prediction under a censored regression model (known as the ' Tobit ' model). In this paper, some selection procedures based on the information theoretic criteria are proposed, and these procedures are proved to be consistent.

关 键 词：删失回归 LAD估计 信息理论准则 模型选择 

分 类 号：O2121[理学—概率论与数理统计]