Date:         Wed, 27 Apr 2005 11:53:59 -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: extracting the names of variable name in a sas dataset
In-Reply-To:  <1114572301.252729.168150@g14g2000cwa.googlegroups.com>
Content-type: text/plain; charset=US-ASCII

"mehtakrishna2002@yahoo.com" <mehtakrishna2002@YAHOO.COM> replied:
> David---You are right. this is a statistical issue in variable
> selection. I do not know beforehand number of variables in the input
> dataset or their names. So  once the dataset gets fed into the program
> the # of variables are determined. Before deciding on the final model
> multiple iterations are run during which variables are deleted. To do
> this I need to define  numrous arrays and I  do it by renaming the
> variables v1-v&nvrs where &nvrs is number of variables. Ofcourse you
> gurus might have an easier solution .

Perhaps if you could write back to SAS-L (not to me personally) and
describe just what kind of variable selection you are doing, and why,
we could simplify your life.  After all, many SAS procs already do a
variety of selection methods.  And, in some other cases, variable
selection methods may not be appropriate.

David
--
David Cassell, CSC
Cassell.David@epa.gov
Senior computing specialist
mathematical statistician