frailtypack: General Frailty models using a semi_parametrical penalized likelihood estimation or a parametrical estimation

Frailtypack now fits several classes of frailty models using a penalized likelihood estimation on the hazard function but also a parametrical estimation. 1) A shared gamma frailty model and Cox proportional hazard model. Left truncated, censored data and strata (max=2) are allowed. Clustered and recurrent survival times can be studied (the Andersen-Gill(1982) approach has been implemented for recurrent events). An automatic choice of the smoothing parameter is possible using an approximated cross-validation procedure. 2) Additive frailty models for proportional hazard models with two correlated random effects (intercept random effect with random slope). 3) Nested frailty models for hierarchically clustered data (with 2 levels of clustering) by including two iid gamma random effects. 4) Joint frailty models in the context of joint modelling of recurrent events with terminal event.

Downloads: