The estimation of average hazard ratios by weighted Cox regression

被引:226
作者
Schemper, Michael [1 ]
Wakounig, Samo [1 ]
Heinze, Georg [1 ]
机构
[1] Med Univ Vienna, Dept Med Stat & Informat, Sect Clin Biometr, A-1090 Vienna, Austria
基金
奥地利科学基金会;
关键词
converging hazards; effect sized; Prentice test; proportional hazards model; survival analysis; weighted estimation; TESTS; TIME; DIAGNOSTICS; CANCER;
D O I
10.1002/sim.3623
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Often the effect of at least one of the prognostic factors in a Cox regression model changes over time. which violates the proportional hazards assumption of this model. As a consequence. the average hazard ratio for such a prognostic factor is under- or overestimated. While there are several methods to appropriately cope with non-proportional hazards, in particular by including parameters for time-dependent effects, weighted estimation in Cox regression is a parsimonious alternative without additional parameters. The methodology, which extends the weighted k-sample logrank tests of the Tarone-Ware scheme to models With multiple, binary and continuous covariates, has been introduced ill the nineties of the last century and is further developed and re-evaluated ill this contribution. The notion of all average hazard ratio is defined and its connection to the effect size measure P(X<Y) is emphasized. The suggested approach accomplishes estimation of intuitively interpretable average hazard ratios and provides tools for inference. A Monte Carlo study confirms the satisfactory performance. Advantages of the approach arc exemplified by comparing standard and weighted analyses of an international lung cancer Study. SAS and R programs facilitate application. Copyright (C) 2009 John Wiley &, Sons, Ltd.
引用
收藏
页码:2473 / 2489
页数:17
相关论文
共 40 条
[31]   Predictive accuracy and explained variation in Cox regression [J].
Schemper, M .
BIOMETRICS, 2000, 56 (01) :249-255
[32]   COX ANALYSIS OF SURVIVAL-DATA WITH NONPROPORTIONAL HAZARD FUNCTIONS [J].
SCHEMPER, M .
STATISTICIAN, 1992, 41 (04) :455-465
[33]  
STRUTHERS CA, 1986, BIOMETRIKA, V73, P363
[34]  
TARONE RE, 1977, BIOMETRIKA, V64, P156, DOI 10.1093/biomet/64.1.156
[35]  
Therneau TM, 2000, STAT BIOL HEALTH
[36]  
Valsecchi MG, 1996, STAT MED, V15, P2763
[37]  
WAKOUNIG S, 2008, INVESTIGATIONS WEIGH
[38]   Estimating cumulative treatment effects in the presence of nonproportional hazards [J].
Wei, Guanghui ;
Schaubel, Douglas E. .
BIOMETRICS, 2008, 64 (03) :724-732
[39]  
WILCOXON F, 1945, BIOMETRICS BULL, V1, P80, DOI 10.1093/jee/39.2.269
[40]  
Xu R, 2000, Biostatistics, V1, P423, DOI 10.1093/biostatistics/1.4.423