2
$\begingroup$

I have been asked to compare an exploratory factor analysis (EFA) to one based on a hypothesized model. The answer in Why would the results of PCA differ from a confirmatory factor analysis? seems to suggest that this is not conventionally done.

I have very little knowledge of this field, but it seems reasonable to want to compare how a model based on prior assumptions/knowledge compares to the one returned by an EFA.

Can anyone expound on this and point me to some specific references? Also can this be done in R (or SAS)?

Improve this question
$\endgroup$
0

1 Answer 1

Reset to default
3
$\begingroup$

My only comment would be that the approaches of the two methods are so very different that it would usually not make much sense to compare them. In exploratory analysis (factor analysis or any other exploratory statistical technique) there is no hypothesis and no attempt to control type I error. In confirmatory analysis the type I error is controlled and formal hypothesis testing is conducted. So how do you compare? One tests hypotheses and the other doesn't.

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.