I am trying to figure out if there exists a relation between the region someone lives in and their ranking of a website. The region variable is categorical, dependent, and spans 11 levels such as the Mountainous regions, Pacific Northwest, etc.

My ordinal independent variable is numbered from 1-9, with 9 being completely satisfied with the website, and 1 being completely dissatisfied.

The problem I am having here is that I am not sure which test to use with the ordinal independent variable. I would normally use the ANOVA but from my understanding I don't have an interval dependent variable here. Does anyone have any thoughts? Thanks!

  • 1
    $\begingroup$ Why insist on that your independent variable is ordinal? Likert-type rating scales are often treated as interval, especially when being predictors. "Ordinal" predictors are always a problem, no satisfactory recipe exists. $\endgroup$ – ttnphns Aug 21 '15 at 22:23
  • $\begingroup$ You may replace the original variable by its ranks. This is one way to "cope" with ordinality - "since distribution on ordinal scale - if to see it as quatitative - is never known, replace it by uniform one". $\endgroup$ – ttnphns Aug 22 '15 at 9:48

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.