home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!usc!howland.reston.ans.net!sol.ctr.columbia.edu!destroyer!gatech!paladin.american.edu!auvm!PO.CWRU.EDU!PAT
- Return-Path: <pat@slc10.INS.CWRU.Edu>
- Message-ID: <9301041452.AA17656@slc10.INS.CWRU.Edu>
- Newsgroups: bit.listserv.edstat-l
- Date: Mon, 4 Jan 1993 09:52:10 -0500
- Reply-To: "Paul A. Thompson" <pat@po.CWRU.Edu>
- Sender: Statistics Education Discussion <EDSTAT-L@NCSUVM.BITNET>
- From: "Paul A. Thompson" <pat@PO.CWRU.EDU>
- Subject: Re: qualitative principal components
- Lines: 32
-
- >
- >I would be interested in this procedure has already been described
- >in the literature, and if anyone has a better method. I would
- >also be interested in readers' reaction to including dummy variables
- >when deriving PC 1, using the correlation matrix to derive the PCs.
- >The theory isn't there, but it seems to work well most of the time.
- >SAS PRINQUAL's approach, I think, is more general, because it
- >tries to predict each variable from the best linear combination
- >of transformations of all the others. But I think this procedure
- >is more prone to non-convergence and convergence to silly scores.
- >In one example, age was transformed sensibly except that the lowest
- >age in the dataset (one year lower than the next lowest) was transformed
- >to a value way off the scale of the rest of the ages. This MAY have
- >been because I was using non-linear-tail restricted cubic splines,
- >and ordinary cubic splines have some tail difficulties.
- >
-
- Interesting approach. I believe (crossing fingers) that the dummy variable
- approach would be related to correspondence analysis, but your use of
- dummy variables is unclear. It could be correspondence analysis, but be
- more explicit.
-
- In general, your approach sounds somewhat new. I would like to see
- not a chi-square, but overall variance accounted for, or stress (difference
- between transformed actual value and model estimate). It is difficult
- to determine your fit from your description.
-
- --
- Paul Thompson, Ph.D. | Department of Psychiatry | (216) 844-7463
- Case Western Reserve University | Cleveland, OH 44106
- ------------------------------------------------------------------------------
- When I hear "family values," I reach for my revolver. - para. Hans Jonst
-