Date: Sat, 18 Nov 2000 06:00:41 GMT
Reply-To: "Andrew H. Karp" <sfbay0001@AOL.COMNOSPAM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: "Andrew H. Karp" <sfbay0001@AOL.COMNOSPAM>
Organization: AOL http://www.aol.com
Subject: Re: SAS code for discriminant analysis
Content-Type: text/plain; charset=utf-8
>Toni Zhang wrote:
>> I have a project of Discriminant Function Analysis to find items that
>> predict group membership to the best possible accuracy for segmentation
>> I know the process it to get each respondent’s probability score of
>> membership into each of the, say 11 segments. There are 6 predict variables
>> that used, they are Q1-Q6. Afterwards, I need to multiply the response on
>> each item by the coefficients and sum all of the scores and add the
>> constant. I then need to compare the 11 scores within each respondent. The
>> respondent is placed in the segment that has the biggest score.
>> I wonder if there is a good SAS code do this all at once. If there is not,
>> what should I do to save the first SAS output and then do the calculation
>> and then compare the 11 scores. If you have created and like some beautiful
>> SAS code, please share with me if you don’t mind.
>Seems to me that PROC DISCRIM does exactly this.
Yes, that is my understanding as well
Andrew H. Karp
Sierra Information Services, Inc.
A SAS Institute Quality Partner in the USA
19229 Sonoma Highway PMB 264
Sonoma, CA 95476 USA