I have a conceptual question related to types of performance analysis of regression models.

In general we have - R Square, Root Mean Squared Error and Mean squared Error to evaluate Regression models.

Then we have ROC AUC curves to evaluate the performance.

Is their anything else we can use to evaluate the model performance apart from these techniques. I have heard about statistical tests being used in performance evaluation but how do we use them once we have a model.

  • $\begingroup$ Afaik statistical tests would be used to measure how significant a difference in performance is, not to measure performance itself. But I don't know everything, let's see if someone has an answer. $\endgroup$
    – Erwan
    Nov 23, 2019 at 0:10


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.