Bioequivalence trials, intersection-union tests and equivalence confidence sets

TLDR

Bioequivalence is essential for generic drug approval in the United States and European Community and is theoretically interesting as a practical equivalence problem. The authors show that intersection‑union tests clarify, simplify, and unify bioequivalence testing, refute the claim that ratio‑based formulations are harder than difference‑based ones, correct misconceptions about confidence‑set coverage, and extend the framework to multiparameter problems. They describe techniques for constructing 100(1−α)% confidence sets that correspond to size‑α bioequivalence tests. They derive a test more powerful than the one currently specified by FDA and EC guidelines.

Abstract

The bioequivalence problem is of practical importance because the approval of most generic drugs in the United States and the European Community (EC) requires the establishment of bioequivalence between the brand-name drug and the proposed generic version. The problem is theoretically interesting because it has been recognized as one for which the desired inference, instead of the usual significant difference, is practical equivalence. The concept of intersection-union tests will be shown to clarify, simplify and unify bioequivalence testing. A test more powerful than the one currently specified by the FDA and EC guidelines will be derived. The claim that the bioequivalence problem defined in terms of the ratio of parameters is more difficult than the problem defined in terms of the difference of parameters will be refuted. The misconception that size-$\alpha$ bioequivalence tests generally correspond to $100(1 - 2 \alpha)%$ confidence sets will be shown to lead to incorrect statistical practices, and should be abandoned. Techniques for constructing $100(1 - \alpha)%$ confidence sets that correspond to size-$\alpha$ bioequivalence tests will be described. Finally, multiparameter bioequivalence problems will be discussed.