Back to the Top
Dear all,
I just want to know that
1) How Analysis (PK & Statistical) differs in case of Single and Two
Phase Study if we have to test for BE of Test (T) and Ref.(R)?
2) In which of the above mentioned two cases (Single and Two Phase)
Bonferroni correction is to be used.
3) Is it true that 90% CI in case of single phase study changes to 95%
CI in case of two phase study if we use Bonferroni correction. Please
give some detail or references
for answers.
4) Please also suggest some references for Add-On Designs.
Thanks in Advance for ur replies.
With Best Regards
Ravi
Back to the Top
Hi,
My Question is, for conducting a BE study (Test t Vs Ref. R) with two
groups of subjects when decision to study a second group of subjects
is based on the results from the first group, which design will be
most appropriate?
How Statistical Analysis differs in case we have to study 2nd group.
Do We need to combine data of both groups. How it will effect
statistical analysis. Do we need to make Bonferroni correction in this
Case?
Thanks and Regards
Ravi
Back to the Top
The following message was posted to: PharmPK
Dear Ravi,
which country are you aiming at?
Regulations differ; currently only Canada, Japan, and South
Africa recommend add-on designs.
You will have to run some tests before groups may be
pooled, but no alpha-correction is mandatory.
See the respective sections of the guidance page:
Canada: http://bebac.at/Guidelines.htm#CA
Japan: http://bebac.at/Guidelines.htm#JPN
South Africa: http://bebac.at/Guidelines.htm#ZA
Sequental designs are mentioned in New Zealand's guideline.
http://www.medsafe.govt.nz/downloads/vol1.doc (5MB!)
For the next revision of the European Note for Guidance (as
of last week in working draft #8) there are discussions on
group-sequential designs (no add-ons!); most likely only one
data-look will be allowed.
As usual in sequential designs the alpha-level of the interim
analysis will be quite low in order to keep the overall alpha
at 0.05.
US-FDA, Brazil-ANVISA: IMHO no way... ;-)
Best regards,
Helmut
Ing. Helmut Schuetz
BEBAC - Consultancy Services for
Bioequivalence and Bioavailability Studies
Neubaugasse 36/11
1070 Vienna, Austria
e-mail helmut.schuetz.-at-.bebac.at
web http://bebac.at/
contact http://bebac.at/Contact.htm
forum http://forum.bebac.at
Back to the Top
The following message was posted to: PharmPK
Dear Dr. Helmut
Thanks for valuable help.
Please help me in this
Suppose we took 30 subject in a study and Study fails, On the basis of
it we calculated no. of subject needed for next study and it comes out
to be 50.
Now my question is can we do next study by adding 20 subjects to study1
and analyzing all the 50 subjects. If yes which design is to be used?
What is its statistical consideration? How statistical analysis of this
type of design differs from Conventional 2x2 crossover design. Do we
need to make alpha adjustment? What are the chances of study2 meeting
the BE criterion.
Does the design to be used come under the category of Add-On design?
Waiting for Reply.
Thanks & Regards
Ravi
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 "Add on Designs and Bonferroni correction" as the subject | Support PharmPK by using the |
Copyright 1995-2011 David W. A. Bourne (david@boomer.org)