Back to the Top
I am designing a three-treatment, three-period, crossover bioequivalence
study. I'm familiar with the FDA-supported "two one-sided t-tests approach"
(or the equivalent "90% confidence interval approach") to analyzing data
from a two-treatment, two-period, crossover bioequivalence study and the
corresponding sample size tables. I've been unable to find any information
on what modifications need to be made when this approach is extended to a
three-treatment design. Does anyone have any insights?
Thanks in advance for any help you can give!
James D. Coyle, Pharm.D.
College of Pharmacy, The Ohio State University
500 W. 12th Ave.
Columbus, OH 43210
Telephone: (614) 292-7103
FAX : (614) 292-1335
Back to the Top
[Two replies - db]
From: Mallikaarjun Suresh
Subject: RE: PharmPK analysis of 3-treatment bioequivalence studies
Date: Fri, 5 Mar 1999 14:00:59 -0500
The following references address this issue :
1. Chow SC, Liu JP - On Assessment of Bioequivalence Under a Higher-Order
Crossover Design, J Biopharm Stats, 2(2), 239-256, 1992
2. Chen KW, Chow SC, Li G - A Note on Sample Size Determination for
Bioequivalence Studies with Higher-Order Crossover Designs, JPB, 25(6),
Suresh Mallikaarjun, Ph.D.
Clinical PK//PD and Metabolism
Otsuka America Pharmaceuticals
From: "shuqiu zhang"
Subject: Re: PharmPK analysis of 3-treatment bioequivalence studies
Date: Sat, 06 Mar 1999 13:15:33 CET
Hi Jim Coyle,
Recently I also worked on statistic analysis for my clinical trial data
=2E As my knoweledge, I think you could use ANOVA, by post hoc or special
contrast method you can compare every pair comparision.
Sernander v=E4g 2:241, s-752 61 Uppsala,Sweden
PharmPK Discussion List Archive Index page
Copyright 1995-2010 David W. A. Bourne (firstname.lastname@example.org)