Date:         Tue, 23 Nov 2010 13:36:35 -0600
Reply-To:     Warren Schlechte <Warren.Schlechte@TPWD.STATE.TX.US>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Warren Schlechte <Warren.Schlechte@TPWD.STATE.TX.US>
Subject:      Re: Crossover trial
Comments: To: dollsai@YAHOO.COM
In-Reply-To:  <201011231856.oANHpV1t007378@willow.cc.uga.edu>
Content-Type: text/plain; charset="us-ascii"

There are models in mixed that can be coded with either a random or a
repeated statement.  Some models require both.

For crossover designs, I have seen coding using the random statement,
and I have seen coding using the repeated statement.

Google "SAS Crossover Mixed" and you should find examples of both
approaches.

The book "SAS System for Mixed Models" uses the random approach.

This blog discusses the issue:

http://blogs.sas.com/sastraining/index.php?/archives/56-Is-It-Random-or-
Repeated.html

This link discusses the use of random and repeated as well.

http://www.mathkb.com/Uwe/Forum.aspx/sas/17310/Mixed-models-when-do-we-n
eed-repeated-and-random

As always, if Dale, Robin, or some of the other MIXED experts find time
to respond, they'll likely give you better and more detailed advice.

Warren Schlechte

-----Original Message-----
From: SUBSCRIBE SAS-L Sharavi [mailto:dollsai@YAHOO.COM]
Sent: Tuesday, November 23, 2010 12:56 PM
To: SAS-L@LISTSERV.UGA.EDU; Warren Schlechte
Subject: Re: Crossover trial

Thanks much.
Do i need to use a repeated or estimate statement or does random
suffice?