- On 20 Feb 2013 at 08:17:48, Christian de Mey (c.demey.at.acps-network.com) sent the message

Back to the Top

The following message was posted to: PharmPK

Dear Forum,

We are planning a relative bioavailability study between a novel peroral

formulation and an established innovator reference; the two formulations

are

expected not to be bioequivalent. The trial is requested to be designed

such

that it meets the requirement that "the SE around the geometric mean

ratio

should be no more than 20%". We know the ANOVA-MSE from previous

XO-studies

with related formulations. How should we estimate the sample size?

Kind regards - Christian

PD Dr. med. Christian de Mey

ACPS - Applied Clinical Pharmacology Services

Philippsring 11, D-55252 Mainz-Kastel, Germany

c.demey.at.acps-network.com

http://www.acps-network.com - On 20 Feb 2013 at 18:06:24, (Peter.Wolna.at.merckgroup.com) sent the message

Back to the Top

Hi Christian,

Usually the confidence interval (90% or 95%) is used as a measure of

precision. The CI (and SEM) get smaller and smaller with increasing the

sample size. So if you set a certain width of the CI (20% translates to

a half-width of 0.223 in log-space), the corresponding sample size is

easily calculated. Can be done using R, nQuery SAS...

Regards,

Peter

Want to post a follow-up message on this topic?
If this link does not work with your browser send a follow-up message to PharmPK@lists.ucdenver.edu with "Sample size estimates for relative bioavailability study" as the subject |

Copyright 1995-2014 David W. A. Bourne (david@boomer.org)