We are happy to announce our seventh online seminar in the Biostatistics Seminar Series on Thursday, February 1st, 16h-17h
This series of Biostatistics seminars targets a broad (bio)statistical audience, in particular PhD-students. Specialists discuss a topic of their interest, paying particular attention to concepts relevant and accessible to a non-specialist audience as well.
Professor Ernst C. Wit
Università della Svizzera italiana
Some inference tricks in event history analysis.
Biostatistics was one of the fields that was at the basis of the development of event history analysis, often called Survival Analysis in this context. Fundamental contributions by Cox, Aalen, Meier, Laird and Carlenius made it an unmissable tool in the toolbox of the applied biostatistician. However, recent challenges require further developments of such models.
With new monitoring systems, time-varying covariates have become more common and incorporating them in standard software can be computationally challenging. On the flip-side, having more data, it can be interesting to model non-linear effects, among which global covariates or even the baseline hazard. In this talk we focus on some computational inference tricks that make that possible.
We apply our model to a species diffusion process in the field of ecology.
Teams link: (no longer available)
Slides: Many thanks to prof. Ernst Wit for allowing us to share the slides here