Positive loadings with PROMAX, negative with OBLIMIN

Posted by Bruce Weaver on Nov 08, 2013; 10:45pm
URL: http://spssx-discussion.165.s1.nabble.com/Positive-loadings-with-PROMAX-negative-with-OBLIMIN-tp5722956.html

Here's another little factor analysis mystery I stumbled across.  I'm using the data file available on this UCLA webpage:  http://www.ats.ucla.edu/stat/spss/output/factor1.htm.  Here's my syntax, with my question at the end.


NEW FILE.
DATASET CLOSE all.

GET FILE='C:\bw\SPSS\data\UCLA\M255.SAV'.

DESCRIPTIVES item13 to item24.

factor
 /variables item13 to item24
 /print initial extraction rotation fscore
 /format blank(.30)
 /criteria factors(3) iterate(100)
 /extraction paf
 /rotation promax
 /method = correlation.

* Factor 3 loadings (from Pattern Matrix) are:  0.781 and 0.821.
* This matches results shown in one analysis on the UCLA web-page.

factor
 /variables item13 to item24
 /print initial extraction rotation fscore
 /format blank(.30)
 /criteria factors(3) iterate(100)
 /extraction paf
 /rotation oblimin
 /method = correlation.

* Factor 3 loadings (from Pattern Matrix) are:  -0.778 and -0.814.

* Q. Why does the sign change when I switch from PROMAX to OBLIMIN? .


My apologies to the EFA experts out there if this is a well-known phenomenon.  (I'm a bit of a duffer when it comes to multivariate stuff, including EFA!)  

Cheers,
Bruce