I run two univariate linear regressions within one sample (same subjects, two different conditions). Now I would like to know how to compare the regression coefficients in order to find out whether they differ significantly. All of the methods I find apply to a case with two different independent samples. How do I do this in SPSS?

  • 1
    $\begingroup$ What would it mean for the coefficients to differ significantly? Eg, if you were looking at something as a function of height & weight, what would it mean for the coefficient on weight to be bigger than the coefficient on height? $\endgroup$ – gung - Reinstate Monica Jul 11 '14 at 16:52
  • $\begingroup$ Yes, it would be helpful if you could make the question more concrete. Is it like you are regressing weight on height before a diet starts and then weight on height after a diet is over --- but on the same set of dieters? $\endgroup$ – Bill Jul 11 '14 at 16:56
  • $\begingroup$ Yes, it is like that, it's repeated measures. I have a sample of subjects and I look how the pre-stimulus response predict the post-stimulus response in two different conditions. so basically I'd like to know whether the preparatory response predicts the post-stimulus significantly stronger in one condition as compared to the other. I hope it's understandable. $\endgroup$ – Lisa Ka Jul 11 '14 at 17:02

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.