I wanted to prove the correlation between 8 variables. I used spss MANOVA

MANOVA S K A E WITH D AC C AS / discrim all alpha(1) / print=sig(eigen dim).

But I don't get the canonical correlation all I get is the regression analysis and I get the following warning:

The WITHIN CELLS error matrix is SINGULAR. These variables are LINEARLY DEPENDENT on preceding ones .. E Multivariate tests will be skipped.

Can anyone please explain to me why I don't have the correlation. Does this mean that there isn't any canonical correlation? If thats the case, is there any other kind of correlation that might be efficient for my data. Thanks.


1 Answer 1


I'm not sure about the MANOVA syntax, but the STATS CANCORR extension command computes canonical correlations. OVERALS, in the Categories option, computes nonlinear canonical correlations.


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.