Non-PH Parametric Survival Modelling

Gilbert MacKenzie (University of Limerick)

Friday 29th May, 2015 15:00-16:00 Maths 204

Abstract

We trace the development of alternatives to Cox's semi-parametric model. The models are 
illustrated by analyzing data from the Northern Ireland Lung Cancer Survival study which identified 
and followed-up 855 incident cases. 
In particular, we review  the derivation of the Generalized Time-Dependent Logistic (GTDL)
regression model which was motivated, in part, with connections to the multiple logistic function.
The GTDL also has deep connections with other well-known statistical distributions. 
However, a problem with the GTDL emerged and its resolution  via the concept of frailty is demonstrated. 
The revised model is shown to perform well in published simulations with competing models. The 
Frailty extension leads, unsurprisingly, to multivariate forms of the GTDL.
Finally, the ideas  surrounding non-PH parametric models are generalized further using the concept
of Multi-Parameter Regression Survival models (MPRS). The basic ideas are illustrated, briefly, using a
MPRS Weibull model. We anticipate that this class of  model will improve practice
in survival analysis.

Add to your calendar

Download event information as iCalendar file (only this event)