0
$\begingroup$

I am performing a MANOVA with a large multivariate dataset representing total body shape (dependent variable). My two independent variables are gender (sex) and cluster (from a previously computed cluster analysis). 

body.shape=cbind(unix,uniy,pw1x,pw1y,pw2x,pw2y)
bshape.manova=manova(body.shape~sex*cluster,data=data)
summary(bshape.manova,test="Wilks")

The output works however, no matter what I do I cannot get the interaction term between the two independent variables (sex*cluster) which is really important. I have run 5 MANOVA's on other populations and it all worked great. This population specifically will not given the interaction between the independent variables and their effect on the dependent variable.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

You can try the function adonis from the vegan package which worked quite well for me on many multivariate analyses.

Note that you should provide a reproducible example including some of your data and results so we can comment on what might be the issue on the interaction term of your MANOVA.

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.