Date:         Tue, 22 Nov 2005 22:01:25 -0500
Reply-To:     Paul Walker <walker.627@OSU.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Paul Walker <walker.627@OSU.EDU>
Subject:      Re: Opinions of Least Angle Regression - for the stats people

Given that interpretation of LARS as linear regression but with a
restriction, e.g. sum(abs(beta))<c, I wondered if GLMSELECT can also be
(appropriately) used with a binary target variable, and if not, whether
such extensions exist in any other new procs?