I have come across a few discussions on this site which state that random oversampling or undersampling doesn't impact the coefficients of the independent variables in logistic regression.

Since the coefficient values are estimated based on the "log-loss" contributed by each & every observation, aren't the coefficient values actually impacted?

What am I missing here?


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.