Date:         Mon, 14 Feb 2011 15:07:11 -0800
Reply-To:     "Nordlund, Dan (DSHS/RDA)" <NordlDJ@DSHS.WA.GOV>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Nordlund, Dan (DSHS/RDA)" <NordlDJ@DSHS.WA.GOV>
Subject:      Re: survey sample size
In-Reply-To:  <201102142248.p1EK7m1T003217@waikiki.cc.uga.edu>
Content-Type: text/plain; charset=utf-8

> -----Original Message-----
> From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
> William Shakespeare
> Sent: Monday, February 14, 2011 2:48 PM
> To: SAS-L@LISTSERV.UGA.EDU
> Subject: survey sample size
>
> Is there a way in SAS to compute survey sample size for complex
> surveys?
> I don't think that proc power will work because the errors are wrong.
> If
> this is not possible in SAS then what software will provide the correct
> sample size estimates?

I am not aware of any software (which does not mean the isn't some), but if you have some estimate of the Design Effect for main analyses of interest (say from similar surveys or previous work), you may get a reasonable sample size estimate by running PROC POWER and multiplying the estimated sample size by the design effect.

Dan

Daniel J. Nordlund
Washington State Department of Social and Health Services
Planning, Performance, and Accountability
Research and Data Analysis Division
Olympia, WA 98504-5204