46% power in study planning? [Study As­sess­ment]

posted by jag009  – NJ, 2013-08-01 22:04 (4301 d 12:39 ago) – Posting: # 11151
Views: 25,833

❝ ❝ Can you elaborate? With T/R of 84% and a CV of 26% you would have needed 342 (!) subjects to obtain 80% power (and still 260 for 70% power – which is the lowest any serious IEC should accept, IMHO). Was your target power only 46% – running another “casino-type” study? Bad.


❝ I Really apologize for the mistake, the ratio is 84.71 and CV for the pilot study is 19.11.


With ISCV=19.11, T/R ratio 84.71, n~140 at 80% power so you were within range with your pivotal study.

If outlier test confirms then one option is to do a rechallenge study -> Run another small study with the questionable subjects along with a few controls.

I assume you tweaked the formulation based on the pilot study data (Ratio 84.71) before going pivotal? Going into a pivotal study with the same formulation is a bit risky IMHO...

John

Complete thread:

UA Flag
Activity
 Admin contact
23,424 posts in 4,927 threads, 1,671 registered users;
74 visitors (0 registered, 74 guests [including 4 identified bots]).
Forum time: 10:43 CEST (Europe/Vienna)

If you shut your door to all errors
truth will be shut out.    Rabindranath Tagore

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