Extracting factor scores - flipped correlations


I've been doing Principal Axis Factoring using 'psych' but encountered problems when extracting the factor scores with the command X$scores. When for instance plotting a correlation matrix using the extracted factor scores the correlations between the factors are perfectly polar opposite or flipped (negative correlations in the PAF are suddenly positive in the matrix). In this case it is easy to double check the matrix since the item-correlations them self make it obvious that something has gone wrong.

Any ideas what the problem may be?

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.