I have a dataset with the variables: id start stop event tempdiff straling The data contains recurrent event, so for each id more than one interval is created and more than one event can occur. I have fitted the next model: mod1 = coxph(Surv(start,stop,event) ~ tempdiff3 + straling3 + frailty(uid) + cluster(uid) , deel1) The model will work when I use the cluster and the frailty function seperately, but in combination I get this error message: residuals.coxph(fit2, type = "dfbeta", collapse = cluster, weighted = TRUE) : length of 'dimnames' [2] not equal to array extent Is there I was I could use both functions in the same analysis? Greetings, Britt -- View this message in context: http://r.789695.n4.nabble.com/Frailty-variable-and-cluster-function-in-coxph-tp4638523.html Sent from the R help mailing list archive at Nabble.com.