删失回归模型的随机加权逼近(英文)  

Randomly Weighting Bootstrap for Censored Regression Models

作　　者：徐瑞锋[1] 方易新[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》2004年第4期384-392,共9页Chinese Journal of Applied Probability and Statistics

基　　金：ResearchpartiallysupportedbyNationalNaturalScienceFoundationofChina(GrantNo.10171094)Ph.D.ProgramFoundationoftheMinistryofEducationofChina.

摘　　要：Rao and Zhao(1992)提出了一种用随机加权的方法去逼近线性回归模型中M-估计的渐近分布.之前,Fang and Zhao(2002)把这种方法推广到设计阵是随机的删失回归模型.本文,我们把这个结果推广到设计阵是非随机的删失回归模型,并证明该随机加权方法的一些大样本性质.Rao and Zhao (1992) developed the random weighting method for M-estimates in regression models. In earlier papers, Fang and Zhao (2002) applied this method in censored regression models with the design points being random. In this paper we extend these results to the situation that the design points are non-random.

关 键 词：删失回归 LAD估计 随机加权 

分 类 号：O212[理学—概率论与数理统计]