I am running a principal components analysis in R using the principal function. When I run my data using varimax rotation (orthogonal) I do not have a problem. However, if I run my data using oblimin rotation (oblique) R gives me a warning that a Heywood case was detected (two of the variables have a loading that is greater than 1). I can't seem to find any documentation on what to do about it. I thought this was more of an issue with factor analysis and that PCA didn't have such issues, but I suppose I am wrong. Is there a way to best handle this issue?


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.