Date:         Thu, 31 Aug 2006 22:19:40 -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: Power Analysis
In-Reply-To:  <200608311136.k7VAkj3P019516@mailgw.cc.uga.edu>
Content-Type: text/plain; format=flowed

learnsassam@YAHOO.COM wrote:
>
>Hi,
>     I am trying to do some power analysis for my study. I have repeated
>measures for 3 time points and the outcome is continuous. I was wondering
>if there is any SAS routine to perform power analysis for repeated
>measures.
>
>Thanks,
>Sam

Power analysis for a repeated measures problem is a really hard
problem.  Are you sure that you need this?  If you have done the
study already, then you can estimate some of the key quantities
that are needed for attempts at this.  Otherwise, you would
have to guess that some previous study would provide reasonable
estimates, and work from that.

Also, since there are several ways to attack a repeated measures
problem, you need to determine if the software out there is
dealing with the methodology that you have used.

And have you checked that all your underlying assumptions are valid?
The power analysis software will have to assume this.  If you have
unmet assumptions, you will not get good results.

HTH,
David
--
David L. Cassell
mathematical statistician
Design Pathways
3115 NW Norwood Pl.
Corvallis OR 97330

_________________________________________________________________
Check the weather nationwide with MSN Search: Try it now!
http://search.msn.com/results.aspx?q=weather&FORM=WLMTAG