I have a Logistic Regression Model in R

m1 <- glm(walz_vote ~ voter_party + voter_age + voter_college + voter_female +
            voter_race + voter_hispanic +voter_urban + voter_county,
          data = data, family = "binomial")

Plotting the linear model looks like this, I'm not super familiar with logistic regression, but from what I know the assumptions of the model failed. How would I go about transforming this?

Assumption plots

  • 1
    $\begingroup$ For logistic regression your response variable should be $\in [0, 1]$, what is yours? $\endgroup$ – Cameron Chandler Oct 26 at 7:24
  • $\begingroup$ You might have a "factor" displayed as an integer" and that can turn your model to junk quickly. Please duble-check. It looks like you are using 'R', so the 'str(data)' command applied to your data will tell you if voter_party or voter_hispanic is integer or factor. If you are using binomial ink, then your output should also be a factor. I don't see that in the residual. How can you get continuous residual from classifier error? I think "family=binomial" might also work. $\endgroup$ – EngrStudent Oct 26 at 17:12

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.