search for


Assessing bioequivalence in 2×3 dual designs
Journal of the Korean Data & Information Science Society 2017;28:743-54
Published online July 31, 2017
© 2017 Korean Data & Information Science Society.

Hwa Hyoung Woo1 · Gyu Jin Jeong2 · Sang-Gue Park3

13Department of Applied Statistics, Chung-Ang University
2Department of Business Statistics, Han Nam University
Correspondence to: Sang-Gue Park
Professor, Department of Applied Statistics, Chung-Ang University, Seoul 06974, Korea. E-mail:
Received June 8, 2017; Revised July 3, 2017; Accepted July 8, 2017.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Assessing bioequivalence between original drug and generic drug is traditionally based on 2×2 crossover design. As bioequivalence trials for highly variable drugs are getting popular, the required sample size based on 2×2 crossover design would be very large, which might cause the ethical concerns. Regulatory agencies like EMA and MFDS recommended higher order crossover designs such as 2×4, 4×2 and 4×4 crossover designs. Alternatively, a 2×3 dual design may be recommended in terms of economical and ethical points of view in comparison with the 2×4 crossover design for highly variable drug. In this study, we consider some statistical characteristics of 2×3 dual design and propose statistical procedures for calculating sample size and assessing bioequivalence based on 2×3 dual design. We also discuss the proposed procedures from the perspective of newly revised bioequivalence guidance issued by MFDS.
Keywords : 2×3 dual design, 2×3 extra reference design, bioequivalence, highly variable drug