Dear all, I use the COXPH function in the SURVIVAL package to estimate survival models with a random effect. I would like to know if there is a measure of "model fit and complexity" analogous to the Akaike Information Criterion implemented in COXPH, in order to compare together models including different sets of covariates (models not necessarily nested within each others). Kind regards, Basile Chaix [[alternative HTML version deleted]]
Maybe Matching Threads
- Survival analysis with COXPH
- estimating survival times with glmnet and coxph
- basehaz() in package 'Survival' and warnings() with coxph
- Is the output of survfit.coxph survival or baseline survival?
- Package "survival" --- Difference of coxph strata with subset?