Bioequivalence and Bioavailability Forum

Dear Pash!

❝ can any one suggest about sample size calculation for parallel study planing on basis of pilot study results or available literature

No big difference to methods for cross-over designs. Don’t forget that in parallel designs only the total variability (between + within subjects) is accessible.

Essentially you have three options:

1. Believe that the CV in your pilot study is a value without uncertainty (I’m notorious for calling that “carved from stone”).
   
2. Take the uncertainty of the CV into account, i.e., use the upper confidence limit of the CV instead of the value itself.
   
3. If you have data from more than one study (either your own ones or from literature), you may pool these CVs. In this case I would strongly suggest to use the CL approach in estimating the sample size.

For option 1 you may use commercial software (PASS, nQuery Advisor,…) or freeware (FARTSSIE, packages bear and PowerTOST for R). AFAIK only PowerTOST (my personal recommendation) allows for options 2 & 3.