jsnell55 wrote: > Please provide an answer with a simple example for this > statistically-challenged researcher.
In general, all other things being equal, the larger the difference between two treatments, the smaller the sample size needed to detect it. Or, the smaller the treatment difference, the larger the sample size needed to detect it. You mention "previous similar studies", so I'm guessing there may be additional information that did not come across in the original post, but has the use of a placebo in this situation been found to be ethical? . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
