Back to the Top
Dear all
Could anyone provide me some references on how to calculate the sample
size (based on the intra-subject variability)for a crossover study of 3
treatments, 3 periods, 6 sequences (Williams design).
So far,I could only find the references for bioavailabity studies
using classic 2 x 2 designs .
Thanks in advance,
Jaime Ilha
Cartesius Analytical Unit
State University of Sao Paulo
Brazil
Back to the Top
The following message was posted to: PharmPK
Dear Jaime,
All my references given for 2x2 designs at
http://www.boomer.org/pkin/PK03/PK2003226.html are also valid for the
6x3 Williams' design - actually they are also valid for any
variance-balanced design with no replicates (every treatment is given
only once).
Good luck,
Helmut
Helmut Schütz Biokinet GmbH / Dept Biostatistics
Neubaugasse 36/11 Nattergasse 4
A-1070 Vienna/Austria A-1170 Vienna/Austria
tel/fax +43 1 9713935 tel +43 1 4856969 62
no cell phone ;-) fax +43 1 4856969 90
http://www.goldmark.org/netrants/no-word/attach.html
[The reference to the archive (that Helmut has included) may change as
new items are added so either use the search function
http://www.boomer.org/cgi-bin/
htsearch?method='and'&sort='score'&words=Sample+size+in+BE&restrict=http
://www.boomer.org/pkin/ or the annual index at
http://www.boomer.org/pkin/PK_2003.html as a more robust way to find
this (and other) item(s) - db]
Back to the Top
The following message was posted to: PharmPK
Dear Jaime
Well I am not a Biostatistician, but I believe if you select two
treatments which show maximum difference or variability, use these
for usual calculations. These will yeild a larger number which is
the answer for you.
Dr. Prashant
PharmPK Discussion List Archive Index page
Copyright 1995-2010 David W. A. Bourne (david@boomer.org)