0
$\begingroup$

I have found a significant positive correlation between 2 ordinal variables collected from likert scale data (Creativity at work and Engagement at work). I used the non parametric Spearmans rho test to calculate this.

I now need to see if this correlation is moderated by generation. Generation is therefore a categorical moderator with 2 levels (Millenial's/non millenial's).

What test should I use to see if there is a significant difference in the correlation between creativity and engagement for Millenials Vs Non Millenials?

$\endgroup$

1 Answer 1

1
$\begingroup$

If one of the variables is conceived of as dependent and the other independent, then you can run a regression with two main effects and an interaction.

If not, then you can stratify on the moderate and then test the difference in the two correlations.

$\endgroup$
2
  • 1
    $\begingroup$ Thanks so much Peter - not too sure what you mean by stratify on the moderate? Does that just mean split my sample into millenials and non millenials? I have done this already, but no idea what test in spss will test the difference in the two correlations? Thanks so much for responding, didn't think I would hear anything back :-) $\endgroup$ Jul 3, 2015 at 11:59
  • $\begingroup$ Yes. Stratifying means splitting your data. I don't use SPSS so I don't know how to do that, but it must be possible. $\endgroup$
    – Peter Flom
    Jul 3, 2015 at 13:14

Your Answer

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

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