- Communications Faculty of Sciences University Ankara Series A1 Mathematics and Statistics
- Vol: 56 Issue: 1
- NON-PROPORTIONAL HAZARDS WITH APPLICATION TO KIDNEY TRANSPLANT DATA
NON-PROPORTIONAL HAZARDS WITH APPLICATION TO KIDNEY TRANSPLANT DATA
Authors : Emel Başar
Pages : 55-63
Doi:10.1501/Commua1_0000000196
View : 8 | Download : 6
Publication Date : 2007-02-01
Article Type : Research
Abstract :The Cox proportional hazards (PH) model is the popular methodfor modelling censored survival data.Cox PH model is the proportionality of hazards in which the hazard ratiois linear in the covariates. However this assumption may not hold in somesurvival studies. Therefore, diğerent non-parametric regression methods havebeen proposed to estimate the hazard ratio as a function of time when theproportionality of hazards can not be assumed.In this study a piecewisemodel and a non-parametric regression spline model have been considered forthe non-proportional hazards. The models have been illustrated with kidneytransplant dataKeywords : Cox regression, Proportional hazards, Regression splines, Survivalanalysis