Good morning at the Stata Forum! Random Survival Forest is specifically suitable for exploratory analysis of right-censored highly correlated complex survival data of prospective cohorts where the outcome is a time-dependent variable [Ann Appl Stat2008;2:841–60.]. I currently work with the Stata16MP / 2 software.

The project I'm working on is the construction of a predictive model based on the Cox model in which the population studied is that of diabetic patients and the dependent variable is heart failure. Could anyone suggest me a Stata program suitable for this type of analysis that I would like to use for the selection of the most important predictors ?

Thanks in advance for your reply