Numbers [Two-Stage / GS Designs]

posted by d_labes  – Berlin, Germany, 2011-02-16 14:45 (5595 d 13:31 ago) – Posting: # 6637
Views: 31,130

(edited on 2011-02-16 15:15)

Ahoy my dear Captn,

my crowdy R code gives for n1=36, CV=30% (but only 100 000 sims):
ratio=1.25 (->alpha)
p(accept BE)= 0.041
p(accept BE, stage 1)= 0.031
% in stage 2= 80.7
mean N= 47.5

ratio=0.95 (->power)
p(accept BE)= 0.836
p(accept BE, stage 1)= 0.676
% in stage 2= 28.9
mean N= 40.7


Seems nearly the result of Potvin et. al.

Regards,

Detlew

Complete thread:

UA Flag
Activity
 Admin contact
23,653 posts in 4,991 threads, 1,571 registered users;
117 visitors (0 registered, 117 guests [including 33 identified bots]).
Forum time: 05:17 CEST (Europe/Vienna)

To propose that poor design can be corrected by subtle analysis techniques
is contrary to good scientific thinking.    Stuart J. Pocock

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