Why is it a problem that your response variable is skewed in regression? Is taking logarithms the only way to solve it?

  • $\begingroup$ Can you show the distribution of the response variable? so, that we can understand how is it, which language are you using R/Python? $\endgroup$
    – Toros91
    May 4 '18 at 7:37
  • $\begingroup$ You might get more detailed responses on Cross-Validated SE. $\endgroup$
    – n1k31t4
    May 4 '18 at 9:51

Taking logarithms is not a one-size-fits-all approach - what if your response is negatively skewed?

"Simple" linear regression assumes that the response variable is normally distributed. If you'd like to perform this kind of regression, then you should probably transform your response variable to be as normal as possible.

There are other approaches / model types to deal with skewed responses - check out the Tweedie family.


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.