home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!usc!sdd.hp.com!swrinde!gatech!europa.asd.contel.com!paladin.american.edu!auvm!BLEKUL21.BITNET!LAAAA02
- Organization: K.U.Leuven (Belgium)
- Message-ID: <STAT-L%93010410353883@VM1.MCGILL.CA>
- Newsgroups: bit.listserv.stat-l
- Date: Mon, 4 Jan 1993 16:34:13 UTC+0100
- Sender: STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
- From: Vuylsteke Magda <LAAAA02@BLEKUL21.BITNET>
- Subject: qualitative variables in principal component analysis.
- Lines: 19
-
- I concentrate on this topic the last ? years. A good approach is coming
- from the University of Leiden in the Netherlands by a group around
- De Leeuw. In '89 they published their ideas in "Non Linear Multivariate
- Analysis". Albert Gifi. John Wiley and Sons.
- PROC PRINQUAL was inspired by these techniques while W.Kuhfeld worked
- together with this group. Is this correct Warren? I have the impression
- that the technique mentioned by some of the list - I lost the name - can
- be compared with the MORALS approach by Jan De Leeuw. But more details
- would be necessary for an exact comparison. Thomson's remark concerning
- correspondence analysis is correct if all the variables are nominal and
- then transformed to dummy variables.
-
- Drs. Magda Vuylsteke Telephone (32)-16-286611 ext2215
- Computing Center Fax (32)-16-207168
- Center of Statistics
- University of Leuven
- de Croylaan, 52a
- 3001 Heverlee E-mail:laaaa02@blekul21
- Belgium
-