Date:         Fri, 3 Jun 2005 22:31:52 -0700
Reply-To:     cassell.david@EPAMAIL.EPA.GOV
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "David L. Cassell" <cassell.david@EPAMAIL.EPA.GOV>
Subject:      Re: Scoring model in SAS
Content-type: text/html; charset=ISO-8859-1

<FONT face="Default Sans Serif,Verdana,Arial,Helvetica,sans-serif" size=2><DIV>Naren &lt;<A href="mailto:naiknaru@REDIFFMAIL.COM" target=blank>naiknaru@REDIFFMAIL.COM</A>&gt; wrote:</DIV><DIV>&gt;I also have the same doubt.. how we can write scoring program without <BR>&gt;Enterprise miner. <BR>&gt; I have written a scoring program using proc factor and proc score in <BR>&gt;base sas. <BR>&gt; Is it proper one..!!?? <BR><BR>Probably.&nbsp; If it fits the way the data actually behave.</DIV><DIV>&nbsp;</DIV><DIV>There really isn't a single correct way to develop scoring models.&nbsp; A lot</DIV><DIV>of different statistical methods can be used, and a lot of different models</DIV><DIV>can be applied.</DIV><DIV>&nbsp;</DIV><DIV>You could also try techniques like logistic regression, GAM, and a host of</DIV><DIV>other methods available in SAS/STAT.&nbsp; See what actually conforms to </DIV><DIV>your data.</DIV><DIV><BR>HTH,<BR>David<BR>-- <BR>David Cassell, CSC<BR><A href="mailto:Cassell.David@epa.gov" target=blank >Cassell.David@epa.gov</A><BR>Senior computing specialist<BR>mathematical statistician<BR></DIV></FONT>