need your help.
I run principal component analysis on the data, and get specific eigenvalues in the SPSS output (in the table "Total variance explained" -> "Initial eigenvalues"). However, when I compute eigenvalues "manually", they differ from those computed with PCA.
Particularly, I use the following syntax commands for "manual" computation in SPSS:
where x is the matrix that contains my variables in the columns. Then I compute x transposed * x, and compute eigenvalues of this matrix.
Interestingly, eigenvalues are different from those I get with PCA.
What can be the problem? Does PCA method in SPSS compute eigenvalues in a different way?
Thanks in advance for any help.