Blind interim in parallel design? [Two-Stage / GS Designs]

posted by Astea – Russia, 2019-06-03 03:47 (1788 d 19:14 ago) – Posting: # 20312
Views: 6,770

Dear Helmut!

❝ I don’t get your subject line. Do you mean that...


I am very sorry for confusing! (neither of them, but I really love your way of thinking!!) It has to mean "Blind men and an elephant", a parable about how difficult is to find the truth if you have only limited data :pirate:. That was about parallel blind studies.
[image]

❝ Simulations… Might be tricky cause we have to think about unequal group sizes and/or variances.


As far as I understood from an article by A. Fuglsang*, heteroscedasticity should not cause problems. But for blind studies CVaverage (that is not distinguishing treatments) is not equal to CVpooled, how to deal with it? Is there a way to prove a possibility of inflation in blind parallel studies?



Complete thread:

UA Flag
Activity
 Admin contact
22,993 posts in 4,828 threads, 1,651 registered users;
113 visitors (0 registered, 113 guests [including 8 identified bots]).
Forum time: 23:01 CEST (Europe/Vienna)

Never never never never use Excel.
Not even for calculation of arithmetic means.    Martin Wolfsegger

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