Next, we will use the predict() function to score the test data in ChurnStudy.test, based upon the prediction model trained on ChurnStudy. The newdata= label designates the new dataset to be stored. The lp type is one of several types used for prediction, and this method uses the linear predictor:
pred_validation <- predict(CoxModel.1, newdata=ChurnStudy.test, type='lp')
The resulting predictions will be in log form.