The required sample size here depends on the level of correlation between binary repeated measures within clusters. We do not always know this in advance. The ideal solution would probably be to use an existing similar study with a known sample size (ie number of clusters) as a pilot study, and to input the standard errors from that into your power calculation.
The general principles behind power calculations for generalized linear models (including those for binary data) are summarized in Newson (2004), which describes how to do them using the -powercal- package, downloadable from SSC,
I hope this helps,
Roger
References
Newson R. Generalized power calculations for generalized linear models and more. The Stata Journal 2004; 4(4): 379-401. Download pre-publication draft from
http://www.imperial.ac.uk/nhli/r.newson/papers.htm
Roger Newson
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: [email protected]
Web page: www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/
Opinions expressed are those of the author, not of the institution.
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Apicella, Louis
Sent: 15 September 2007 14:39
To: [email protected]
Subject: st: sample size calculation for binary repeated measures
Hello Statalisters,
I am trying to determine the sample size for a binary repeated measures study in which we'll collect baseline data from two groups, intervention and control, then expose the intervention group, followed by collecting data twice more post-intervention from both groups.
I've been using this code to come up with sample sizes
sampsi .45 .55, sd1(.5) sd2(.5) power(.8) method(ancova) pre(1) post(2) r1(.5) r01(.5)
My question is that I have only proportions to work with and I'm not sure that sampsi is designed to use proportions when we specify sd1() and sd2().� I also feel that the variance should be closer to .1 for each sample but then my sample size is ridiculously small (n=8).� Essentially, what I want to be able to do is a comparison of the change in the intervention group to the change in the control group. Any ideas?
Thanks,
Lou.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
