dataMultiv

This contains simulated data with two different types of recurrent event times and a terminal event time from a multivariate frailty models with two gaussian random effects. This data set is useful to illustrate how to fit a multivariate frailty model.
This database combines different observations for each subject (sample size=250, number of lines=1237 so in average four recurrent events per subject). The right-censored case is treated only and the calendar timescale representation is used. Exponential death times and recurring times are generated using a gaussian  multivariate frailty model. The frailty terms are iid $N(0,0.5)$ and correlated with $\rho=0.5$ and $\alpha1=0.6$ and $\alpha2=-0.3$, the coefficient associated with the frailty term in the death time hazard function, is set at 0. The right-censoring variable is set at 5 and the covariate is generated from a Bernoulli distribution (p=0.5).

datasets

Frailtypack now fits several classes of frailty models
        using a penalized likelihood estimation on the hazard function
        but also a parametric estimation. 1) A shared frailty model
        (with gamma or log-normal frailty distribution) and Cox
        proportional hazard model. Clustered and recurrent survival
        times can be studied. 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 for recurrent
        events with terminal event for clustered data or not.
        Prediction values are available. Left truncated (not for Joint
        model), right-censored data, interval-censored data (only for
        Cox proportional hazard and shared frailty model) and strata
        (max=2) are allowed. In each model, the random effects have a
        gamma distribution, but you can switch to a log-normal in
        shared and joint models. Now, you can also consider
        time-varying covariates effects in Cox, shared and joint
        models. The package includes concordance measures for Cox
        proportional hazards models and for shared frailty models.

dataMultiv: Simulated data with two types of recurrent events and a dependant terminal event

Description

Usage

Arguments