1
$\begingroup$

In my study, I have two age groups (YA and OA) and 3 scores (A, B, C) are collected from each participant. Here I'm interested in two dependent variables, "RCG" which is calculated by subtracting B from A and "DSC" which is calculated by subtracting C from A. I'm planning to run an MANOVA test with age group as the independent variable and RCG and DSC as two dependent variables. I'm expecting to find an interaction such that there is a group difference in DSC but not in RCG.

As both RCG and DSC are calculated from score A, I assume they are not completely independent from each other. Would this be a violation of the MANOVA assumptions? The correlation between RCG and DSC is about 0.5.

Is there another statistical method that is more appropriate to use here?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

MANOVA is a multivariate analysis method created just to be able to model dependence between outcome/response/dependent variables, so you are certainly not violating assumption for that reason.

Improve this answer
$\endgroup$

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.