I am interested in testing whether certain variables with a high correlation between them should be removed from the model.
I was thinking of checking this out with VIF.
I am working with a data set with a binary y and with significant imbalance problems (99: 1).

Could the imbalance hurt the multicollinearity indications that VIF is supposed to help me find?

  • $\begingroup$ You could investigate it by simulation, but if you use the VIF as defined for linear regression, it does not depend on $Y$ so answer is clear. But if you use some gvif for glm's could be different? Please ad details, which vif do you use? $\endgroup$ – kjetil b halvorsen Aug 17 '20 at 2:41

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.