Bioequivalence and Bioavailability Forum

Sample size, alpha, beta, beta/2 and that all [General Sta­tis­tics]

posted by d_labes  – Berlin, Germany, 2015-02-05 10:31 (4152 d 21:36 ago) – Posting: # 14376
Views: 11,677

Dear Astea,

don't fiddle too much with the formulas given by Chow, Wang and who ever co-authors. There are many typing errors or hidden, not explained assumptions in the mentioned paper and book.

IMHO the only correct way to estimate the sample size is 'brute force', i.e. choose a sample size, estimate power and than iterate sample size until desired power is reached.

All other ways are more or less approximations to tackle the problem avoiding the not so easy power calculations. But in the ages where PowerTOST is available there is no need for such approximations .

These attempts are only useful for obtaining a reasonable start value for 'brute force'. As such they are used within PowerTOST.
Have a look at

Paul Zhang (2003)
"A Simple Formula for Sample Size Calculation in Equivalence Studies"
Journal of Biopharmaceutical Statistics, 13:3, 529-538

to get the formulas used (including z_1-ß or z_1-ß/2 and such things).

Complete thread:

• MSE calculation jag009 2012-09-13 17:39 
  • MSE calculation from CI of 3x3x3 study d_labes 2012-09-14 09:43
    • Oops! Helmut 2012-09-14 14:31
      • Oops? One or two-tailed? ElMaestro 2012-09-14 15:48
        • One or two-tailed? d_labes 2012-09-17 09:57
          • One or two-tailed? Astea 2015-02-05 01:20
            • Sample size, alpha, beta, beta/2 and that alld_labes 2015-02-05 09:31
              • Sample size, alpha, beta, beta/2 and that all Astea 2015-02-07 12:53
                • Sample size, alpha, beta, beta/2 and that all d_labes 2015-02-07 16:22
    • MSE calculation from CI of 3x3x3 study jag009 2012-09-24 20:12
      • MSE calculation from CI of 4x4x4 study d_labes 2012-09-25 10:40
        • MSE calculation from CI of 4x4x4 study jag009 2012-09-25 14:59
      • MSE calculation from CI of 3x3x3 study ElMaestro 2015-02-05 12:57