Dear Colleagues,
Does anyone know of a method for accurately back calculating the power of an
equivalence test for the difference in two proportions based on a confidence
interval
The problem is this. The original specification said that equivalence would
be demostrated if the lower 95% confidence limit did not exceed 10%. The
observed value was 10.6%. However the expected success rates were higher
than those used in the power calculation leaving the study under powered.
But I would like to know by how much.
Thanks in advance
Bruce
_________________________________________________________________
Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp
|