1
$\begingroup$

I'm trying to find a test that will allow me to test the relationship between a categorical dependent variable and several independent variables that are both continuous (interval) and ordinal.

If there is no such test, it would also makes theoretical sense for me to turn the variable "around". That is, I could use a statistical test (if such exists) that allows me to test the effect of a categorical independent variable on several dependent variables that are both continuous and ordinal.

I hope this makes sense and would be grateful for any help.

Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ There are numerous questions and answers relating to modelling this sort of data; you might be able to find a few (and hence get some additional help) by using the search facility with appropriate keywords. $\endgroup$
    – Glen_b
    Commented Aug 26, 2014 at 22:52

1 Answer 1

Reset to default
4
$\begingroup$

What software are you using? Sounds like multinomial logit would be a good fit, if the categories are mutually exclusive and not ranked (for example, political party, university attended, etc.).

For Stata, that would be mlogit dependentvar independent1 independent2 [etc.]

If the relationship could go either way, I would definitely use caution in reporting results (like every stats teacher says, correlation does not equal causation!), and state why you first wanted to test the relationship this direction and not the other way.

Improve this answer
$\endgroup$
1
  • $\begingroup$ Thank you! I use SPSS, which I see includes multinomial regression. And yes agree, I do need to consider and justify the direction of the relationship. $\endgroup$
    – user54750
    Commented Aug 27, 2014 at 0:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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