数学物理学报 ›› 2014, Vol. 34 ›› Issue (3): 530-539.

• 论文 • 上一篇    下一篇

多元失效时间数据的一般边际半参数危险率模型研究

杨青龙1|郭丽莎2|刘妍岩3   

  1. 1.中南财经政法大学统计与数学学院 武汉 430073;
    2.中南民族大学数学与统计学院 武汉 430073;
    3.武汉大学数学与统计学院 武汉 430072
  • 收稿日期:2012-02-11 修回日期:2013-12-13 出版日期:2014-06-25 发布日期:2014-06-25
  • 基金资助:

    国家自然科学基金 (11171263,  11301545)和中南财经政法大学基本科研业务费青年教师创新项目(20132051) 资助

A General Class of Marginal Semiparametric Hazards Model with Multivariate Failure Time Data

 YANG Qing-Long1, GUO Li-Sha2, LIU Yan-Yan3   

  1. 1.Zhongnan University of Economics and Law, Wuhan 430073;
    2.School of Mathematics and Statistics, South Central University for Nationalities, Wuhan 430073;
    3.School of Mathematics and Statistics, Wuhan University, Wuhan 430072
  • Received:2012-02-11 Revised:2013-12-13 Online:2014-06-25 Published:2014-06-25
  • Supported by:

    国家自然科学基金 (11171263,  11301545)和中南财经政法大学基本科研业务费青年教师创新项目(20132051) 资助

摘要:

在生物医学研究中, 多元失效时间数据非常常见.  该文提出用一般边际半参数危险率回归模型来分析多元失效时间数据.
此模型包括了三种常用边际模型: 边际比例风险模型、边际加速失效时间模型和边际加速危险模型作为子模型. 对于模型中的回归系数, 可以通过估计方程的方法来估计它, 同时也给出了基准累积危险率函数的估计. 得到的估计可以证明是相合的和渐近正态的.

关键词: 多元失效时间, 边际危险模型, 估计方程, 渐近正态

Abstract:

Multivariate failure time data are frequently encountered in biomedical research. In this article,  we propose a general class of hazards regression model for multivariate failure time data. This general class includes some popular classes of models as subclasses,  such as marginal proportional hazards model, the marginal accelerated failure time model.
 Regression coefficients are estimated through estimating equation method. The proposed estimators for the  regression parameters are shown asymptotically to follow a multivariate normal distribution with a sandwich-type
covariance matrix that can be consistently estimated. The estimated subject-specific cumulative baseline hazard process is  shown to converge weakly to a zero mean Gaussian random field.

Key words: Multivariate failure time, Marginal hazards model, Estimating equation, Asymptotic normality

中图分类号: 

  • 62G05