Hi,
I am a novice biostatistician. I want to know how to compute sample size for bio equivalence study with two treatment, two sequence and two perionds.
The formula for sample size calculation is given (Eq 11.7.0, page no 478, Design and Analysis of clinical trial, Chow and Liu, 2nd edition) as:
Now I am finding two difficulties.
1. I have only following informations with me
a. geometric means and 90% confidence intervals for the ratio Drug A / Drug B is 104.69% and (90% CI = 93.21% - 117.59%)
b. sample size used 26
c. desired alpha =0.05 and power= 80%
With this informations of previous study I want to compute sample size of a forthcoming bioequivalence study of Drug A and Drug B.
For this at first I have to compute estimate of sigma-d for the application of the above formula. I think sigma –d is the Root Mean Square Error of the ANOVA model. So I find out estimate of sigma-d in the following way:
From the ANOVA the no difference region for comparing two treatments mean is:
Therefore,
= Width of the Confidence Interval = U – L (say)
It reduces to
I have done this using my simple understanding in Statistics. So please tell me whether this is perfectly right …… or there should be anything else.
2. What is the meaning of and what should be its interpretation?
Looking forward to get suggestions
Thanks and regards,
Madan
--------------
Madan Gopal Kundu
Biostatistician and SAS Programmer
Ranbaxy R&D
Gurgaon, Haryana
India
Web: http://www.freewebs.com/madanstata
mobile: 91-9868788406
e-mail: [log in to unmask]
Click to join Statisticians_group
---------------------------------
Jiyo cricket on Yahoo! India cricket
Yahoo! Messenger Mobile Stay in touch with your buddies all the time.
|