Dear R users, I'm trying to fit a survival model using the survreg function with a Weibull distribution. I'm using the frailty() function in order to fit a "family" random effect in my model. I would like to calculate the estimate for each observation and I know the predict() function doesn't work with mixed models. Hence, I was wondering if I could use the output model$frail and model$linear.predictors to do this. Would anyone have an advice on this topic? Best regards, Nicolas N. Rode PhD student CEFE (Centre d'Ecologie Fonctionnelle et Evolutive) 34293 Montpellier, France -- passerelle antivirus du campus CNRS de Montpellier -- [[alternative HTML version deleted]]