Bioequivalence and Bioavailability Forum • Sample size feasible

Sample size feasible [RSABE / ABEL]

posted by d_labes – Berlin, Germany, 2012-02-08 10:47 (4826 d 02:17 ago) – Posting: # 8071
Views: 21,439

Dear AB,

if your point estimator is ok (i.e. in the range 0.95 ... 1.0526) a sample size estimation with your ISCV and a full replicate design (2-sequence-4-period) gives (using R with package PowerTOST)

library(PowerTOST)

sampleN.TOST(CV=0.47, design="2x2x4")



+++++++++++ Equivalence test - TOST +++++++++++

            Sample size estimation

-----------------------------------------------

Study design:  2x2x4 replicate crossover 

log-transformed data (multiplicative model)



alpha = 0.05, target power = 0.8

BE margins        = 0.8 ... 1.25 

Null (true) ratio = 0.95,  CV = 0.47



Sample size (total)

 n     power

44   0.806110

Thus the chance with a feasible sample size is greater then anticipated by my previous speaker above :cool:

.

But the question remains: Why do you resist in using the 80-125% acceptance range also the EMA allows you a widening :confused:

. Or is your ISCV from AUC?

—
Regards,

Detlew

Complete thread:

ISCV and CI AB 2012-02-08 08:21 [RSABE / ABEL]
- ISCV and CI drgunasakaran1 2012-02-08 08:44
- Sample size feasibled_labes 2012-02-08 09:47
  - Sample size feasible AB 2012-02-08 11:40
    - No worries! Helmut 2012-02-08 13:37
    - Sample size down! d_labes 2012-02-08 14:18
      - World record? Helmut 2012-02-08 14:31
        
        Wow! d_labes 2012-02-08 16:16
        
        Wow! Helmut 2012-02-08 16:24
        
        Wow! AB 2012-02-08 16:48
        
        World record? jag009 2015-09-23 20:43
        
        Nope Helmut 2015-09-23 21:57