Back to the Top
Dear all
I would like to know how I can calculate confidence
interval (CI) for AUC or Cmax in a parallel design in
a bioequivalence study. Is it correct to calculate F
relative (AUC test/AUC ref)in parallel designs.
Although it has been noted for doing this in
crossover studies but I have not find a clue in BE
guidelines for parallel studies.
Any comment or guidance is appreciated
Thanks
Ali Rassouli
Dept. of pharmacology
Faculty of Vet Med
University of Tehran
Back to the Top
Ali
Yes you can compute CIs for a parallel group design. Once you take
the natural log of AUC or Cmax, the problem is transformed to
determining the (1-alpha)% CI for the difference in means. Then you
exponentiate the result to determine the ratio of means.
Hope this helps,
Pete Bonate
Back to the Top
The following message was posted to: PharmPK
Dear Ali,
for worked examples see these two threads:
http://forum.bebac.at/mix_entry.php?id=616
http://forum.bebac.at/mix_entry.php?id=674
Best regards,
Helmut
Ing. Helmut Schuetz
BEBAC - Consultancy Services for
Bioequivalence and Bioavailability Studies
Neubaugasse 36/11
1070 Vienna, Austria
e-mail helmut.schuetz.aaa.bebac.at
web http://bebac.at
forum http://forum.bebac.at
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@boomer.org with "Confidence interval 90% in parallel designs" as the subject | Support PharmPK by using the |
Copyright 1995-2011 David W. A. Bourne (david@boomer.org)