Dipesh Jayswal
●    

2007-03-13 11:38
(6225 d 04:17 ago)

Posting: # 573
Views: 6,587
 

 Sample size for 2waycrossover BE from Parallel BE or 3way BE [Power / Sample Size]

Dear HS,

I have two questions regarding sample size determination for BE study:

1. is it possible to estimate sample size for 2way crossover from parallel BE study????

2. Assume that we have a data for 3way crossover(3 period - 6 sequence) pilot - BE study in which two test products(T1 and T2) were compared with RLD. Now we want to go ahead with either of the test formulation (i.e. either T1 or T2) to be compared with RLD in 2way crossover(2 period - 2 sequence) pivotal study, then how to estimate the correct Sample Size for it???

please suggest me way out or some reading on it????

Thanks in advance.

Dipesh
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2007-03-13 13:50
(6225 d 02:05 ago)

@ Dipesh Jayswal
Posting: # 574
Views: 5,442
 

 Sample size for 2x2 Xover BE from Parallel BE / 3way BE

Dear Dipesh!

❝ 1. is it possible to estimate sample size for 2way crossover from parallel

❝ BE study????


No! :-(
From a parallel study you only get information on the total variability (= between and within, or inter- and intra- subject); there is no way to extract the intra-subject CV from this kind of study.
One thing is granted: CV-intra < CV-total ;-)
For some drugs CV-total is >50%, but CV-intra <10%...

❝ 2. Assume that we have a data for 3way crossover(3 period - 6 sequence)

❝ pilot - BE study in which two test products(T1 and T2) were compared with

❝ RLD. Now we want to go ahead with either of the test formulation (i.e.

❝ either T1 or T2) to be compared with RLD in 2way crossover(2 period - 2

❝ sequence) pivotal study, then how to estimate the correct Sample Size for

❝ it???


It's quite reasonable to apply the CV-intra from the 3×6 study in sample size estimation for the pivotal 2×2.

❝ please suggest me way out or some reading on it????


S-C Chow and J-p Liu
Design and Analysis of Bioavailability and Bioequivalence Studies
Marcel Dekker, New York, 2nd Ed. (2000)

S Patterson and B Jones
Bioequivalence and Statistics in Clinical Pharmacology
Chapman & Hall, Boca Raton (2006)

D Hauschke, V Steinijans and I Pigeot
Bioequivalence Studies in Drug Development - Methods and Applications
John Wiley & Sons, Chichester (2007)

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Dipesh Jayswal
●    

2007-03-13 14:31
(6225 d 01:24 ago)

@ Helmut
Posting: # 575
Views: 5,321
 

 Sample size for 2x2 Xover BE from Parallel BE / 3way BE

Thanks a lot HS for ur reply..

i know that from total variability it is not possible to separate out the intra CV as u suggested. Thanks for ur confirmation.

regarding intra CV% from 3way crossover BE study, it is the mixture of all the the three formulations. I wanted to know that is it possible to estimate intra CV for RLD and either T1 or T2.

thak u again for ur prompt reply.

Regards,
Dipesh

Edit: Full quote removed. [HS]
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2007-03-13 14:43
(6225 d 01:12 ago)

@ Dipesh Jayswal
Posting: # 576
Views: 5,455
 

 Replicate design!

Dear Dipesh!

❝ regarding intra CV% from 3way crossover BE study, it is the mixture of all

❝ the the three formulations. I wanted to know that is it possible to

❝ estimate intra CV for RLD and either T1 or T2.


It's not possible to obtain the variability of treatments for a 3×6 design (as it's not possible for a 2×2 design), since you have administered each of the 3 formulations only once.

In order to get information on the variability of formulations, a replicate design is needed.

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Dipesh Jayswal
●    

2007-03-14 09:08
(6224 d 06:47 ago)

(edited by HS on 2007-03-14 11:47)
@ Helmut
Posting: # 577
Views: 5,259
 

 Replicate design!

Dear HS,

Thanks for ur clarification.

--
Edit: Full quote removed. [HS]
UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,638 registered users;
76 visitors (0 registered, 76 guests [including 9 identified bots]).
Forum time: 15:55 CET (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5