Search code examples
rsurvival-analysiscox-regression

Cox regression : Are we supposed to keep the status column for test?

From the examples that I have seen for cox-regression:

http://www.sthda.com/english/wiki/cox-proportional-hazards-model ,

the data includes the status or event column as well.

But if I wish to train the cox model on train data, and then use the trained model for prediction, should I keep the 'status' column in test data?

Also, how are we supposed to predict probable duration of survival for a test sample?

Solution

  • I have found that in both R and python survival packages the status column is included for train and test.