[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Differences between stata 9 and 8.2 - factor analysis
At 10:39 AM 6/20/2005 -0700, you wrote:
If everything is the same except the factor loadings have all switched
signs, doesn't that mean that the old and new factors are perfectly
negatively correlated? If so, does it matter which one you "trust?"
Thanks for the hint. Yes, you are right, as expected the results are the
same as in the real 8.2 when I use -version-. My only problem now is
that I have to figure out what exactly the difference between the two
version is and which one I should trust (and how to justify that). The
whatsnew just tells me that rotate has been expanded with new methods of
rotations, but I don't see how that should affect my usage of VARIMAX.
I guess something has been changed on how that rotation works, perhaps a
starting value? Any clues?
Even if it doesn't, the change seems odd, and I agree that the reasons are
not clear from the online help alone. Perhaps the new Multivariate
Statistics Manual contains the details, but nothing stood out when I did a
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: