Power calculation from Partial replicate study [General Sta­tis­tics]

posted by jag009  – NJ, 2013-05-16 18:18 (4771 d 13:38 ago) – Posting: # 10592
Views: 3,000

Hi all (I think Helmut will hate this topic heheh).

Would the following code be applicable for partial replicate study also?

lbl=log(.8);
ubl=log(1.25);
ci=90;   /*either 90 or 95 */      
p=(1-(CI/100))/2;
ctt=tinv(p,df); 
ctt=abs(ctt);
t1=ctt+(lbl/StdErr);
t2=-ctt-(ubl/StdErr);
p1=probt(t1,df); p2=probt(t2,df);
pwr=1-(p1-p2);   
pwr=ROUND(100*pwr,0.01);

From Proc GLM (of FDA's HVD SAS RSABE code), I can extract the df and StdErr.

I know this is a post-hoc thingy but am just interested.

Thanks
John

Complete thread:

UA Flag
Activity
 Admin contact
23,653 posts in 4,991 threads, 1,570 registered users;
261 visitors (0 registered, 261 guests [including 42 identified bots]).
Forum time: 07:57 CEST (Europe/Vienna)

The epistemological value of probability theory is based on the fact
that chance phenomena, considered collectively and on a grand scale,
create non-random regularity.    Andrey Kolmogorov

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