‘Two-at-a-Time’ approach with >3 treat­ments [Design Issues]

posted by Shuanghe  – Spain, 2022-07-10 02:05 (266 d 05:39 ago) – Posting: # 23123
Views: 937

Hi Helmut,

❝ long time, no hear!

Indeed. COVID, change of company and workload, study, ..., Pretty busy these days. Had to work day and night recently to catch everything up, so I had much less time to read the forum than before... But I'll be in Amsterdam this September for the 5th global BE harmonisation conference, so hopefully we'll have time to have a drink together :smoke: :smoke: :smoke:

By the way, the Article section is new, am I right? (Don't tell me I missed this section all those years...) I am supprised that no one mentioned it in the forum. I don't have time to read the lengthy ones yet but I really enjoy the reading among the few short ones that I've picked.

❝ All extracted IBDs are balanced.

What I understood about balanced IBD here is that, e.g., the number for A vs. F comparison should be same as number of F vs. A. So there should be 10 for each comparison for 20 in total.

If that is a correct understanding, it seems that for B, C and D, yes, but for A and E, not... There're 11 AF (FE) but 9 FA (EF). Shouldn't it be 10 and 10 like B/C/D vs F?

❝ If you run the script, the chance to get the same sequences like in my example is 1/120.

I tried the code and obviously I cannot reproduce your result as you said, but among the few runs I had, there is a run with 8 EF and 12 FE, 11 FA (BF) and 9 AF(FB)...

All the best,

Complete thread:

UA Flag
 Admin contact
22,560 posts in 4,725 threads, 1,607 registered users;
23 visitors (0 registered, 23 guests [including 10 identified bots]).
Forum time: 07:45 CEST (Europe/Vienna)

No written law has ever been more binding than
unwritten custom supported by popular opinion.    Carrie Chapman Catt

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