## Blind 2Stage [Two-Stage / GS Designs]

Hi Nastia,

» But can you clarify me the meaning of blindness in BE trials?

You know its meaning.
Never seen ones, except for Health Canada:

2.4.2 Blinding
To avoid study bias, comparative bioavailability studies should be conducted in such a way that the subjects are not aware of which product (test or reference) is being administered.

That’s a funny idea if the products don’t look the same.

» […] it turns out that blinding may even worse the situation (5.01% vs 7.36%, TIE). It is connected with the unknown PE (cause for BLIND=TRUE s20s<-mses), but isn't it contrintuitive?

Yes and yes. Have a look at Figure 1 of Golkowski et al.*

» Can it be true for parallel design also? Suppose we want to make a blind interim analyses after first stage with N subjects and recalculate sample size on fixed GMR=0.95 if total CV would be greater than initial suggestion. Will it cause any inflation?

Possibly.

» How to estimate it?

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

BTW, do you remember Paola Coppola’s presentation at last year’s BioBridges?

• Golkowski D, Friede T, Kieser M. Blinded sample size re-estimation in crossover bioequivalence trials. Pharm Stat. 2014;13(3):157–62. doi:10.1002/pst.1617.

Cheers,
Helmut Schütz

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