Bioequivalence and Bioavailability Forum

manual power calculation: why? [Power / Sample Size]

posted by Helmut  – Vienna, Austria, 2011-03-28 16:40 (5554 d 10:17 ago) – Posting: # 6824
Views: 8,930

Dear Karthik!

❝ how to calculate power without using any software?

At least you need a pocket calculator and tables of the t-distribution.

For approximations see

Hauschke D, Steinijans VW, Diletti E and M Burke
Sample Size Determination for Bioequivalence Assessment Using a Multiplicative Model
J Pharmacokin Biopharm 20/5, 557-561 (1992)

Why don’t you use free software (FARTSSIE for Excel, package PowerTOST for R)?

❝ or what are all the parameters we want consider to calculate power?

With given α (patient’s risk, commonly 5%), acceptance range (commonly 80–125%), expected T/R-ratio, and sample size you get power.
If you want to calculate sample size for target power (e.g., 80%), increase the sample size until calculated power ≥ target power. Sample size calculation is always an iterative procedure. See one of my presentations.

Complete thread:

• manual power calculation Karthik 2011-03-17 10:17 [Power / Sample Size] 
  • manual power calculation: why?Helmut 2011-03-28 14:40
    • manual power calculation: why? K2K 2012-01-16 12:56
      • FARTSSIE.xls Helmut 2012-01-16 13:14
        • FARTSSIE.xls K2K 2012-01-16 13:21
          • CV from CI: manual, PowerTOST, FARTSIE.xls Helmut 2012-01-16 14:27
            • CV from CI: manual, PowerTOST, FARTSIE.xls K2K 2012-01-18 09:35