Date:         Wed, 30 Nov 2005 16:01:15 -0500
Reply-To:     Peter Flom <flom@NDRI.ORG>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Peter Flom <flom@NDRI.ORG>
Subject:      Re: Influential observations
In-Reply-To:  <BAY103-F23044F573D38A768CFDAF5B04A0@phx.gbl>
Content-Type: text/plain; charset=US-ASCII

I think Paige wrote

>I wonder why you say this. If the original poster knew which
variables
>were causing the multicollinearity problem, he probably would have
>acted as you suggest and removed some of the variables causing
>multicollinearity.

If the original poster does not know this, then he can discover it
through the use of the
/collin option on PROC REG.  This not only shows how much collinearity
there is, but also
which variables are involved.

Peter