0
$\begingroup$

I'm trying to compare the effect of an IV on my DV, where my data are separated into 3 groups. Specifically, in one group there is a significant correlation between IV and DV, but in the other two groups this is much weaker. I would like to test this effect and was thinking that multiple linear regression seems to be the appropriate method.

I have followed the instructions detailed here:

https://stats.idre.ucla.edu/spss/faq/how-can-i-compare-regression-coefficients-across-three-or-more-groups/

to compare regression coefficients among 3 groups in SPSS and they work perfectly for my data set, however, if I understand it correctly the very last step tests the null hypothesis; Ho: B1 = B2 = B3, which doesn't seem to be what I want, because I want to know if B1 = B2 or B2 = B3

Thanks for any help,

Rod.

$\endgroup$

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.