[R] frailtypack - Model did not converge

[Andreu Ferrero]

Hey,


I am using "frailtyPenal" to fit a general joint model:

I got a "Model did not converge" message, and I guess it is because I miss
specify something in the command:

"Call:
frailtyPenal(formula = Surv(Time_final_mes_cor, BD_RE2.Re_IC1_cor) ~
    cluster(BD_RE2.e_b_id) + (BD_RE2.X.a_probnp_bnpR) +
(BD_RE2.ae_presencia_Cizquierda) +
        (BD_RE2.CKD_EPI60) + terminal(BD_RE2.death1_cor),
formula.terminalEvent = ~(BD_RE2.X.a_probnp_bnpR) +
    (BD_RE2.ae_presencia_Cizquierda) + (BD_RE2.CKD_EPI60), data = BD_AV,
    recurrentAG = FALSE, jointGeneral = TRUE, n.knots = 20, kappa =
c(10000,
        10000), maxit = 700, LIMlogl = 0.0142)


  General Joint gamma frailty model for recurrent and a terminal event
processes
  using a Penalized Likelihood on the hazard function

   Convergence criteria:
   parameters = 6.81e-09 likelihood = 0.0115 gradient = 1

   n= 2473
   n recurrent events= 406
   n terminal events= 195"


Any idea??? Cause PC computing takes hours to "fit/non-fit" this model.


Thanks,




Andreu Ferrero Gregori

	[[alternative HTML version deleted]]