BE: ♀♂ [Design Issues]

posted by Helmut Homepage – Vienna, Austria, 2020-05-23 17:12 (157 d 04:56 ago) – Posting: # 21458
Views: 1,224

Salam Loky do,

» […] participants are both males and females, should the ratio between them be 1:1 …

The FDA requires „subjects from the general population”; hence ~1:1. Though I have seen studies in males only as well. Possibly the ANVISA requires that as well.
AFAIK, in other jurisdictions there are no rules.

» … or any ratio is accepted, …

See above. I once saw a study were the protocol stated “females and males” and the the CRO recruited one female and 15 males. The study was accepted by European agencies but it looked stupid.

» … also for randomization procedure is there any special requirements in case both included?

See this thread and R-code for stratification there. IMHO, in crossover designs it does not make sense. Do we have “sex” as an effect in the model? No. Do we want to demonstrate BE separate for females and males? Generally not. If yes, we would have to double the sample size.
Parallel designs are another story, of course. Females/males should be evenly assigned to treatment groups.

Dif-tor heh smusma 🖖
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

Activity
 Admin contact
21,179 posts in 4,414 threads, 1,474 registered users;
online 3 (0 registered, 3 guests [including 3 identified bots]).
Forum time: Tuesday 21:08 CET (Europe/Vienna)

No computer has ever been designed
that is ever aware of what it’s doing;
but most of the time, we aren’t either.    Marvin Minsky

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