st: Sample size estimation using GEEs

["Mark Marshall" <mrmarsh@woosh.co.nz>]

I wish to determine the optimal sample size for a clinical trial of
intervention versus placebo where the outcomes are repeated measures. 

I can do this in Stata with a repeated measures ANCOVA using the sampsi
command. However, this looks a little odd in the grant application when I
then propose GEEs or GLMs in the statistical plan for data analysis.

There is a package in R and Splus called longpower which codes Liu and
Liang's formula for linear GEE models (page 941). I gather there is also a
package is SAS which codes Rochon's formula. There are probably many more
variations on these approaches published in different papers, but I gather
these are the most popular. 

Is there a user friendly Stata ado file that codes any of these
formulae/approaches?

Thanks,

Mark Marshall
AKL, NZ


Liu G, Liang KY. Sample size calculations for studies with correlated
observations. Biometrics. 1997;53:937-47.

Rochon, J. Application of GEE procedures for sample size calculations in
repeated measures experiments.  Statistics in Medicine. 1998;17, 1643-1658.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/