Date:         Wed, 26 Jun 2002 10:28:26 -0700
Reply-To:     Dale McLerran <stringplayer_2@YAHOO.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Dale McLerran <stringplayer_2@YAHOO.COM>
Subject:      Re: A Kronecker dependent variable
Comments: To: M Rose <xtr5@yahoo.com>
In-Reply-To:  <3D19D214.8ACE455D@yahoo.com>
Content-Type: text/plain; charset=us-ascii

Menahem,

Take a look at the MIXED procedure with error structures UN@CS or
UN@AR(1) or UN@UN specified on a repeated statement.  Also, in the
past month there was another thread on time series and cross-sectional
model fitting.  If you go to

http://listserv.uga.edu/cgi-bin/wa?S1=sas-l

and search for TSCSREG since 25 MAY 20002, then you should see all
the posts related to that thread.  In particular, let me point you
to my post on the subject which is linked below:

http://listserv.uga.edu/cgi-bin/wa?A2=ind0205E&L=sas-l&P=R18460

Dale


--- M Rose <xtr5@YAHOO.COM> wrote:
> Hello all,
>
> I would appreciate any help in creating a kronecker structured
> dependent
> variable.
> I have a column variable that I would to expand into a diagonal
> matrix
> where each
> Diagonal cell is the column vector.
> Basically, I need to create a cross-time cross-section model, with
> different slopes per
> Section.
>
> Thank you,
>
> Menahem R.


=====
---------------------------------------
Dale McLerran
Fred Hutchinson Cancer Research Center
mailto: dmclerra@fhcrc.org
Ph:  (206) 667-2926
Fax: (206) 667-5977
---------------------------------------

__________________________________________________
Do You Yahoo!?
Yahoo! - Official partner of 2002 FIFA World Cup
http://fifaworldcup.yahoo.com