I now have a set of data where the outcome is continuous count data but does not follow normal distribution. IV analysis relies on linear regression, in which normality is an important assumption. Can I use IV analysis with a non-normal outcome?

  • $\begingroup$ For linear regression, the residuals or the error terms obtained after the regression have to be normally distributed. The assumption is that "errors are normally distributed". Your model should be good to go as long as the error terms satisfy this assumption. $\endgroup$ Jun 24 at 11:13


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.