Frailty Models - Hierarchical Survival Regressions

[NathanielF]

Frailty Models

Frailty Models - Hierarchical Survival Regressions:

Why should this notebook be added to pymc-examples?

I want to expand the examples in the survival analysis section. I think minimally we should have a more detailed example of survival analysis regression using many predictors and discuss how to output individual predicted survival curves, cumulative hazards etc. The foundations for this are already in: https://www.pymc.io/projects/examples/en/latest/survival_analysis/survival_analysis.html
Bug i think PyMC would benefit from a more explicit and detailed example.

I would also seek to demonstrate how to augment the Cox regression models with individual, shared and correlated frailty terms. This is a type of hierarchical/random effects model used in survival analysis to account for unobserved heterogeneity. In the Cox regression case it means a term is added a multiplicative factor on the hazard terms.

Suggested categories:

• Level: Intermediate
• Diataxis type:

Related notebooks

Cover related notebooks on which this notebook will build,
make sure that the notebook is not duplicated and
explain whether it should be a new notebook or extend an existing one.

References

Will refer to discussions in David Collett's book: Modelling Survival Data in Medical Research.