Frailty models that yield proportional hazards

被引:16
作者
Aalen, OO
Hjort, NL
机构
[1] Univ Oslo, Sect Med Stat, N-0317 Oslo, Norway
[2] Univ Oslo, Dept Math, Math Inst, N-0316 Oslo, Norway
关键词
compound Poisson process; cumulative damage process; frailty; Levy process; proportional hazards;
D O I
10.1016/S0167-7152(02)00090-1
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Proportional hazards is commonly assumed in survival analysis. This assumption appears to be mainly a mathematical convenience, made in order to interpret Cox models in a simple manner. There remains the questions of whether this assumption is actually true to reality in a sufficient number of cases, and whether the assumption relates to other ways of modelling survival data. We shall look at the latter issue, in pointing out that certain frailty models may yield proportional hazards in a natural way. We consider frailty distributions determined by Levy processes. In our framework, the hazard ratio may be interpreted as the ratio between the squared coefficients of variation of the frailty distributions. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:335 / 342
页数:8
相关论文
共 6 条
[1]  
Aalen O O, 1994, Stat Methods Med Res, V3, P227, DOI 10.1177/096228029400300303
[2]  
Aalen O.O., 1992, ANN APPL PROBAB, V2, P951, DOI DOI 10.1214/AOAP/1177005583
[3]   Analyzing incidence of testis cancer by means of a frailty model [J].
Aalen, OO ;
Tretli, S .
CANCER CAUSES & CONTROL, 1999, 10 (04) :285-292
[4]  
BERTOIN J., 1998, Levy Processes
[5]  
HJORT NL, 2002, IN PRESS HIGHLY STRU
[6]  
Hougaard P., 2012, ANAL MULTIVARIATE SU