Imbalanced randomization sequence before conducting the study [Design Issues]

posted by Mohamed Yehia  – Egypt, 2018-01-11 21:36 (2321 d 07:28 ago) – Posting: # 18170
Views: 2,189

❝ While it is a tradition to aim for balance I don't think there is a strong scientific argument against imbalance at the design stage.

❝ I am leaning towards thinking it can be done, but of course you may ask why anyone would aim for an imbalance of one. […]

❝ If on the other hand you have failed to source enough Test or Ref units so that IMP availability creates a bottleneck then certainly the whole ordeal could be kind of dodgy from the outset perhaps and power could suffer a lot?

❝ So let us hear the actual background, please.

Thanks a lot for your detailed reply. The actual background is that I only have 66 tablets of the reference product of a highly variable compound which means that i can only enter the study with maximum number of 33 volunteers. So, after making the sample size calculations I have found that it's better to conduct the study using the 2x2x4 approach over the 2x3x3 and despite the fact that it will not matter that much if we enter the study with 32 volunteers instead of 33 applying the 2x2x4 approach, but I am thinking about that there is a huge possibility that some.of the volunteers may be withdrawn due to any reasons. That's why I am trying to get benefit of each tablet of the reference.

However, as I said before that i m not leaning towards doing what I stated above as in my opinion if I decided to use the 2x2x4 approach then I have to enter the study with even number in order to be balanced although I know that the study may end with odd number. But I believe that the design from the beginning should be applied to minimize the variations in the study as possible as can. So entering the study from the beginning with 16 volunteers with sequence 1 and 17 volunteers with sequence 2 would be a negative point in the design of the study.

Edit: Full quote removed. Please delete everything from the text of the original poster which is not necessary in understanding your answer; see also this post #5! [Helmut]

Complete thread:

UA Flag
 Admin contact
23,033 posts in 4,835 threads, 1,647 registered users;
33 visitors (0 registered, 33 guests [including 3 identified bots]).
Forum time: 06:05 CEST (Europe/Vienna)

Give me a fruitful error any time, full of seeds, bursting with its own corrections.
You can keep your sterile truth for yourself.    Vilfredo Pareto

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