Bioequivalence and Bioavailability Forum

Dear MGR,

in a three-period replicate design (e.g. TRT/RTR) you get not only CV_intra (like in a 2x2 cross-over), but also the reference's (and test's) variability - which may be used in Reference Scaled ABE. Similarly in a four-period replicate design (e.g. TRTR/RTRT) you get the variability of both formulations, which may be used in Population and Individual BE.
Even in a conventional evaluation (ABE) of a replicate study, you are less prone to be hit by outliers. If a subject shows an irregualar response to a treatment compared to the rest of the study's subjects in one period only, you have strong evidence that a subject-by-formulation can be excluded. Sometimes FDA allows exclusion of the subject in such a case (the EU is more strict in this respect).

If you want to go with an extended acceptance range for C_max (0.75-1.33) in the EU, you must demonstrate high variability of the reference in a replicate design pilot study (Q&A document):
8. What is a "highly variable drug or drug product?"
A drug product is called highly variable if its intra-individual (i.e. within-subject) variability is greater than 30%. A high CV as estimated from the ANOVA model is thus an indicator for high within-subject variability. However, a replicate design is needed to assess within-subject variability.

Regards,
Hermann

Hi MGR!

❝ Can anyone please tell me the statistical advantages of Replicate cross over design?

Come on! You are one of the veterans here and have already helped others specifically on this topic here and here. Don't try to turn into a troll.