Which method is NOT an appropriate way to score new observations with a known target in a logistic regression model?
Which method is NOT an appropriate way to score new observations with a known target in a logistic regression model?
Rerunning the LOGISTIC procedure with augmented data that includes new observations is not an appropriate way to score new observations with a known target. This method involves refitting the model, which is unnecessary and inefficient when simply scoring new observations. Scoring should be done using the trained model, either through the SCORE statement in the LOGISTIC procedure or another appropriate scoring method.
I am not sure how B is also a way to score a new observation?