This post is about different functions of the survival package, like basehaz, predict.coxph, survfit, termplot, what kind of results they provide and how they are calculated.
This blog shows how to externally validate a Cox regression prognostic model according to all steps in the paper of Royston & Altman
. R code available.
With the function psfmi_perform
of the psfmi package it is possible to combine Cross-validation with Multiple Imputation for internal validation.
External validation means that the performance of a prediction model is studied in a new (external) patient dataset that is not used to develop the model. It is important to use the correct predicted probabilities to evaluate if the external validation of the model is successful!
With the psfmi_stab function of the psfmi package it is possible to do important stability analyses of the models and predictors selected during backward selection after multiple imputation.