PowerTOST and Sample size estimation for R-SABE [RSABE / ABEL]

posted by mittyri – Russia, 2015-06-25 12:43 (3522 d 17:19 ago) – Posting: # 14986
Views: 14,155

Dear Astea,

I completely agree with the Detlew's post above.
Let me explain some additional issues.

❝ As far as I know SampleN.scABEL simulates studies to get the target power so it would be erroneously just to calculate sample size using SampleN.TOST and scale thetha1 and theta2, wouldn't it?


Absolutely!
Please compare the results:
sampleN.scABEL(theta0=0.90, CV=0.5, targetpower=0.8, design="2x2x4")
and
sampleN.TOST(alpha=0.05, targetpower=0.8, theta0=0.9, theta1=0.6984, theta2=1.4319, CV=0.50, design="2x2x4")

❝ It doesn't fit in my head because there exist replicate studies completed with more than 50 subjects... It turns that it was redundantly?


That's not so easy...
When you performed first study with replicate design in Russia, the Sponsor wasn't sure - is it possible to wide the limits or not. Even after "the carving in red book"...
AFAIK now we can use all advantages of replicate designs in our studies, experts already approved some protocols with scABEL.

From then onward no full replicate studies with 60 subjects for sartans :-D
The most illustrative graph you can find in the Helmut's lecture (slide 98)

Kind regards,
Mittyri

Complete thread:

UA Flag
Activity
 Admin contact
23,380 posts in 4,914 threads, 1,665 registered users;
88 visitors (0 registered, 88 guests [including 14 identified bots]).
Forum time: 05:02 CET (Europe/Vienna)

When people learn no tools of judgment
and merely follow their hopes,
the seeds of political manipulation are sown.    Stephen Jay Gould

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