home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Subject: (no subject given)
- Path: sparky!uunet!europa.asd.contel.com!paladin.american.edu!auvm!COMPUSERVE.COM!71020.1025
- Apparently-To: sas-l@ohstvma.bitnet
- Message-ID: <9211130307.AA04340@ihc.compuserve.com>
- Newsgroups: bit.listserv.sas-l
- Date: Thu, 12 Nov 1992 22:03:49 EST
- Reply-To: William Kahn <71020.1025@COMPUSERVE.COM>
- Sender: "SAS(r) Discussion" <SAS-L@UGA.BITNET>
- From: William Kahn <71020.1025@COMPUSERVE.COM>
- Lines: 41
-
- Bcc: Blind Recipients List:;
- Subject: Conjoint Experts
- Message-ID: <921113030348_71020.1025_EHC59-1@CompuServe.COM>
-
- I have wondered how to do optimal design with comparisons comparisons.
-
- Scenerio: 3 factors: A (5 level class)
- B (price:continuous, linear and quadratic)
- C (2 level class)
- 10 possible products we can build (5x2), price to be determined.
- We want to know which product is most likely to be bought.
- We have a random sample of 17 people from an identified population of
- potential purchasers we can test.
-
- We want a design where triples of possible products are presented, and the
- subject ranks the three items. We presume that if the products are
- identical, except for price, the lower priced object will be prefered (I
- suppose it would be, but perhaps there would be times when people would
- actually prefer to spend more? another discussion there).
-
- Each subject can rank 10 triples before tiring out.
-
- Question: How do we choose an optimal set of triples for each subject?
- Seems like each subject should not necessarily be ranking the same triples.
-
- Joe S. perhaps suggests that optex may be be useful for this design. I
- don't see how. It is clear to me that 170 triples rankings should be able
- to give me information on how to balance product design vs. price, and
- should give me a measure of between subject and within subject variability.
- I have no idea how to do this design. Don't know how to analyze either.
-
- There is a PC program called Best Choice which does part of this via a
- proprietary algorithm. No stochastic measures of its estimates though.
-
- Is Conjoint Analysis what I need to study?
-
- Thanks
-
- William Kahn
- W. L. Gore and Associates
- 71020.1025@compuserve.com
-