Dear group,Back to the Top
could someone provide me general info or reference on the rules and
procedures for determination of sample size and power in clinical trials
many thanks
sinisa
Sinisa Stipanicic, MS Chem.
PLIVA Research Institute Ltd.
Drug Metabolism and Pharmacokinetics (DMPK)
Prilaz baruna Filipovica 25
10000 Zagreb, CROATIA
Phone: +385 1 372 2572
Fax: +385 1 372 1570
Hi Sinisa:Back to the Top
try the archive of this forum - there is quite a lot that you may
consider useful.
For a starters also see ICH guidelines
http://www.ich.org/MediaServer.jser?.-a-._ID=485&.at._MODE=GLB
or for practical applications you could give it a go at
http://hedwig.mgh.harvard.edu/sample_size/size.html
Hope this helps
Hanns
Dr. med. Hanns-Christian Tillmann
Medical Science Leader
Biomit Inc.
Hochstrasse 31
CH-4053 Basel
Switzerland
Phone: +41 (0)61 206 12 71
Fax: +41 (0)61 206 12 22
Email: hanns-christian.tillmann.-at-.biomit.com
Homepage: www.biomit.com
SinisaBack to the Top
"could someone provide me general info or reference on the
rules and procedures for determination of sample size and
power in clinical trials"
This is perhaps too general a question to answer in this forum.
Nevertheless the power of experiments (whether test-tube, animal, human)
to show a result can be simplified to consideration of a signal to noise
ratio. The questions therefore are: what is the signal you are trying
to observe, how accurately can you make the observation and what is the
level of background noise. Designing an experiment that maximises your
ability to observe the presence of a signal (should a signal be present)
would have high power.
Clearly, this is a gross oversimplification of what you need to consider
but it might help you to put together the right sorts of questions to
ask your clinical team.
Regards
Steve
Stephen Duffull
School of Pharmacy
University of Queensland
Brisbane 4072
Australia
Tel +61 7 3365 8808
Fax +61 7 3365 1688
Email: sduffull.at.pharmacy.uq.edu.au
www: http://www.uq.edu.au/pharmacy/sduffull/duffull.htm
PFIM: http://www.uq.edu.au/pharmacy/sduffull/pfim.htm
MCMC PK example: http://www.uq.edu.au/pharmacy/sduffull/MCMC_eg.htm
I use nQuery and found that it is reasonable for BE and other studies.Back to the Top
http://www.statsol.ie/nquery/nquery.htm
PharmPK Discussion List Archive Index page
Copyright 1995-2010 David W. A. Bourne (david@boomer.org)