Which makes it extremely difficult to use the Cox Time Varying Fitter

[stefan-de]

Recently I worked on a project for modeling transitions in a multi-state model with the CTVM. And I would like to share with you what would make the usability of this model more convenient:

• (cumulative) baseline hazard with confidence bounds
• a method which provides cumulative hazard at t for give data x_t (with confidence bounds)
• computation of concordance index
• computation of integrated brier score
• feature selection procedures
• competing risk framework for modelling cumulative incidence functions etc.