Date:         Tue, 5 Nov 2002 18:47:58 -0000
Reply-To:     s.k.tagg@strath.ac.uk
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Dr. Stephen Tagg" <s.k.tagg@strath.ac.uk>
Organization: CRM Institute, University of Strathclyde
Subject:      Re: MDS
In-Reply-To:  <006501c26fcf$edc63ae0$48a096d0@oemcomputer>
Content-Type: text/plain; charset="us-ascii"

You can also get prefmap through http://www.newmdsx.com/

Dr Stephen K Tagg


-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
james watts
Sent: 09 October 2002 21:11
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Fw: MDS

Don't know a way in SPSS, but the former SPSS product Systat has the
PREFMAP
routine which will regress attributes against the vectors formed by two
dimensions.  In the case of PREFMAP the dimensions are from a principal
components run.  I've seen PREFMAP in other program packages.  It's from
the
Bell Labs MDS library of fortran routines.  Here's an address for their
library: http://www.netlib.org/mds/
There's an email address under the PREFMAP you could try for getting the
compiled version.  Jim Watts

----- Original Message -----
From: "Toni Gril" <toni.gril@aragon.si>
Newsgroups: bit.listserv.spssx-l
To: <SPSSX-L@LISTSERV.UGA.EDU>
Sent: Wednesday, October 09, 2002 6:11 AM
Subject: MDS


> Hi!
>
> Does anybody know how to regress variables on the coordinates for the
> different
> dimensions in the MDS solution, e.i. how to get SPSS to make property
> fitting. In other words to project external variables into the two-dim
> space.
>
> Toni
>
>