Cox regression models with nonproportional hazards applied to lung cancer survival data

The Cox regression model, which is widely used for the analysis of treat-ment and prognostic e®ects with censored survival data, makes the as-sumption of constant hazard ratio. In the violation of this assumption, di®erent methods should be used to deal with non-proportionality of hazards. In this study, the strati¯ed Cox regression model and extended Cox regression model, which uses time dependent covariate terms with ¯xed functions of time are discussed. The results are illustrated by an analysis of lung cancer data in order to compare these methods with respect to Cox regression model in the presence of nonproportional hazards