Dear R users, the frailtypack package, for the analysis of correlated survival data, has been updated on CRAN. The major changes in version 2.6 are: * Fit now a multivariate gaussian frailty model (two types of recurrent events and a terminal event). For instance here is a model that fits a weibull multivariate gaussian frailty model with different adjustments: * modMultiv.weib <- multivPenal(Surv(TIMEGAP,INDICREC)~cluster(PATIENT)+v1+v2+ event2(INDICMETA)+terminal(INDICDEATH),formula.Event2=~v1+v2+v3, formula.terminalEvent=~v1,data=dataMultiv,hazard="Weibull") * * New dynamic tool of prediction probabilities in Cox models, standard shared frailty models or joint frailty models. * Concordance measures for clustered data. * initialization of regression coefficients, variance of the random effects, and alpha now available in joint frailty models. Moreover, with 'Alpha="none"', frailtyPenal can fit a joint model with a fixed alpha (=1). * Interval-censored frailty models. Best regards, Virginie Rondeau, Alexandre Laurent [[alternative HTML version deleted]] _______________________________________________ R-packages mailing list R-packages@r-project.org https://stat.ethz.ch/mailman/listinfo/r-packages