0
$\begingroup$

I believe a latent self-control variable may be at the root of plenty of the variation I see in my dependent variable. However, I am using a secondary dataset and do not have access to individual questionnaire scores - all I have is a number of related total scale scores. Can I carry out PCA on these?

The total scale scores are for each of the big five personality traits, the scales within the Strengths and Difficulties Questionnaire, among some other standardised psychological questionnaires. I want to include about 15 of these in the factor analysis. Each participant has completed all of the questionnaires.

$\endgroup$
  • $\begingroup$ I think this needs more detail. What are these "total scale scores"? Is there one for each person or more than one? If more than one, how many? $\endgroup$ – Peter Flom Mar 14 at 11:20
  • 1
    $\begingroup$ Hi Peter, love your stuff on Quora. The total scale scores are for each of the big five personality traits, the scales within the Strengths and Difficulties Questionnaire, among some other standardised psychological questionnaires. I want to include about 15 of these in the factor analysis. Each participant has completed all of the questionnaires. $\endgroup$ – Emmet Mar 14 at 22:18
  • $\begingroup$ Thanks Emmet. Please put that info in your question and then it can be re-opened. $\endgroup$ – Peter Flom Mar 15 at 10:39
0
$\begingroup$

Yes, you can do PCA on the scale scores. But it's not clear what you would get, if you had one PC. Some people have found correlations among some pairs of the 5 factors. You might find this paper interesging. "The general factor of personality: A meta-analysis".

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.