Sample Size and CV for Replicate Design [Power / Sample Size]

posted by ElMaestro  – Denmark, 2011-11-26 23:38 (5330 d 15:57 ago) – Posting: # 7729
Views: 11,102

Hi JamesMartinn,

❝ I'm told that the intra-subject variability, expressed as %CV of a measured response is expected to be 35%. I'm asked to find the sample size in order to have 80% confidence that the estimated CV% is larger than 30%. Assume I'm planning to do a 2x4 Crossover, Replicate design. That is, I will be looking at TRTR and RTRT.


❝ I'm completely lost on how to approach the question. Any direction or guidance in answering this particular question will be much appreciated. I have access to SAS and R. Please advise.


You should download Detlew Labes' R package called PowerTOST.
It will allow you to calculate the sample size (number of subjects) needed to achieve a given power under a set of assumptions and given a design. You have a 2-sequence, 4 period, 2 treatment design, and that's fairly common and easily handled by this package. You do not need to understand all the stats in order to use that tool.

This forum is a great resource. If you use the search function you will probably find discussions about relevant or related issues.

Good luck.
EM.

Complete thread:

UA Flag
Activity
 Admin contact
23,656 posts in 4,994 threads, 1,570 registered users;
257 visitors (0 registered, 257 guests [including 21 identified bots]).
Forum time: 16:36 CEST (Europe/Vienna)

Try to learn something about everything
and everything about something.    Thomas Henry Huxley

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5