search

drizopoulos / JMbayes

Joint Models for Longitudinal and Survival Data using MCMC
59 stars 24 forks source link

DIC Question Not Answered #59

Closed ngwali closed 4 years ago

ngwali commented 4 years ago

Hello Dimitris;

Hope this shouldn't be a burden on your part. But there was one question about the DIC for the Joint Model which you did not answer. I get DIC for the mixed effect submodel. But After combining the Mixed Effect with the survival submodels, how can we calculate the DIC of this Joint Model.

For my situation, I simply compare models based on AUC and PE. i.e to choose from Value, or Value + Slope, or Cumulative effect.

Sorry for the numerous questions sir. I am ok with the AUC and PE. Though the Joint model DIC is better here for making informed decisions.

Thanks :)

drizopoulos commented 4 years ago

Yes, this calculation is not currently performed in JMbayes for mvJointModelBayes() models. It will be available in the new JMbayes2 package.