I'm learning EFA (again autodidactically -_- bloody middle east).. So I hope you help me with this naive question


I have a questionnaire made, and I was able to extract 5 factors. Factor 1 was loaded on 8 variables. Factor 2 on 5 variables.. and so on.. I saw the pattern, I understood it, and I named the factors, now the questionnaire is ready to be published.

My question is:

To score new participants on, say Factor 1, am I going to find the mean of its constituent variables (i.e. the 8 variables aforementioned) for each participant ? and that is it?

Or am I going to use weights extracted from my EFA output (the loadings matrix) to sum the constituting variables of Factor 1? In which case I expect that I need to attach attach the scoring equation with my article, right?

Why am I lost?

We were taught that the Big Five are calculated from the 30 facets by averaging 6 facets for each Big Five factor (i.e. the NEO-PI).

But some resources have also said that they should be weighted. This is where I got lost. When are they weighing and when they are normally averaging? Or am I understanding something wrong?


Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.