2
$\begingroup$

I have a quick question about factor analysis from different scales. Is it advisable to use, conjunctly, items from different measures? For example, if I am interested in doing EFA in the context of mental health, is it advisable to include items from several different scales that have already been published? On one hand, these items have already been shown to do a good job of measuring mental health, but on the other, wouldn't they already cling together?

If it isn't advisable, how do we actually begin gathering items for exploratory factor analysis? Do we just take a wild guess?

Improve this question
$\endgroup$
1
  • $\begingroup$ Here is two distinct themes. 1) FA as a statistical/mathematical analytic technique to reduce correlated variables to latent features and possibly to interpret them. 2) What are the best practices in psychology (or other social disciplines) to plan and apply FA as a method to construct, validate or modify questionnaries. As for the (2), a better place to ask about that is on a psychology/psychometric forum. That said, your question isn't quite off-topic here, too. It might be answered, perhaps, if you put more focus and ask about more concrete problem(s). $\endgroup$
    – ttnphns
    Aug 11, 2022 at 1:17

1 Answer 1

Reset to default
0
$\begingroup$

Maybe you can do the rescaling to the value of the items using techniques such as min-max normalization if the minimum and maximum value of the items are known. By using that, all the values of the items are scaled to 0 - 1, and then you can revert all the values of the items to any scale that you want uniformly.

Improve this answer
$\endgroup$

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.