Date:         Wed, 1 Dec 2004 16:55:33 -0800
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: Saving System weighted R square in Proc syslin
In-Reply-To:  <751633cc.0412011609.7787958f@posting.google.com>
Content-type: text/plain; charset=US-ASCII

Microstructure <randistan69@HOTMAIL.COM> wrote back:
> How can I save the system weighted R square to a sas output file that
> is obtained in  Proc Syslin (using sur).  I know that the command
> outest will not work.

Uh-oh.  You seem to have ignored my previous post.  I really
doubt you should be using SUR, given the models you showed us
before.  You have strongly related regressions, with the Y in
each showing up as an independent variable in the other.  You
have an econometric model which might be better tackled under
a different methodology.  Please go talk to a real econometrics
expert and get this straightened out.

That said, there is no way to get the system-weighted R-squared
in the OUTEST= table.  OUTEST= produces a table of estimates
and information on those estimates.  That is not an appopriate
place for system-level fit statistics.  Use ODS with the TRACE
keyword to get a list of all the tables that PROC SYSLIN generates,
and you'll see which table holds your statistic.

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