|Date: ||Tue, 20 Sep 2005 15:14:05 -0700|
|Reply-To: ||David L Cassell <davidlcassell@MSN.COM>|
|Sender: ||"SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>|
|From: ||David L Cassell <davidlcassell@MSN.COM>|
|Subject: ||Re: PROC GLM - weighting participants by no. of subgroups|
|Content-Type: ||text/plain; format=flowed|
>I'm wondering how to weight participants by number of subgroups per factor
>level in a between-subjects ANOVA using PROC GLM.
>(final goal is to compute MS comparison and MS error for planned contrasts)
I'm not sure I understand what you're asking. If you want planned
can use the CONTRAST statement, and you don't need to weight the
in order to do that.
For that matter, I cannot tell if you should be using PROC GLM, or if you
need PROC MIXED. It depends on your data and your model.
The 'weight participants' part also makes me wonder if you have a survey
with sample weights, in which case you ought to be using PROC SURVEYREG
David L. Cassell
3115 NW Norwood Pl.
Corvallis OR 97330
Express yourself instantly with MSN Messenger! Download today - it's FREE!