1
$\begingroup$

I'm doing a factor analysis and using the resulting factors in a regression. I'm using SAS. A number of the variables load positively on a factor. In order to make it easier to interpret in the final regression, it would be better if the loadings were negative.

Is there a way I can rotate the factor so the loadings are negative? Could the factors be multiplied by $-1$?

$\endgroup$

marked as duplicate by amoeba, Peter Flom Jan 16 '15 at 10:47

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • 2
    $\begingroup$ Yes: see stats.stackexchange.com/questions/34396. The SAS details, if you need them, are best asked on SO rather than here. $\endgroup$ – whuber May 14 '13 at 18:22
  • 1
    $\begingroup$ Yes, the loadings (and consequently the scores) of a factor can be multiplied by -1. Most FA implemementations actually do it internally: if sum of negative loadings is greater than the sum of positive ones, the sign is reverted. $\endgroup$ – ttnphns May 15 '13 at 6:23

Browse other questions tagged or ask your own question.