F. Javier Rubio (KCL, UK)
Title. Net survival models: The Good, The Bad, and The Ugly
Abstract. In the first part of the talk, I will discuss the "relative survival" framework, the idea of "excess hazards" modelling, and the concept of "net survival" (which is the main quantity of interest in descriptive cancer epidemiology). I will present a parsimonious hazard regression model based on the combination of a general hazard structure and a flexible parametric baseline hazard. This hazard structure contains, as particular cases, proportional hazards, accelerated hazards, and accelerated failure time structures. In the second part of the talk, I will discuss a challenge in the context of excess hazards modelling, which is related to the estimation of individual hazards, associated to other causes of death, based on insufficiently stratified life tables. I will present a possible solution to this problem using a parametric correction based on a frailty hazard regression model. I will conclude with a real-data application and a discussion about the challenges in using the relative survival framework in cancer epidemiology.
Seminar organiser: Kalliopi Mylona
[log in to unmask]
The group runs a regular seminar programme on Thursday afternoons, currently 14.00 in room S5.20 on the Strand Campus (Strand, London WC2R 2LS).
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|