Bioequivalence and Bioavailability Forum • Sample size for a pilot study to estimate the CVintra

Sample size for a pilot study to estimate the CVintra [Power / Sample Size]

posted by yjlee168 – Kaohsiung, Taiwan, 2010-03-02 00:47 (5553 d 21:38 ago) – Posting: # 4846
Views: 13,190

Dear Helmut,

Thank you for your message.

❝ statisticians, because we would need some priors in this case. Actually the questions is: how small can a pilot study be that with a certain confidence the sample size estimation for the pivotal study is reliable?

Exactly.

❝ Main hint: The larger, the better. OK, that's trivial, but let's play around with the formula (balanced 2×2 studies), upper 80% CL of CV_intra:

❝ n 10% 15% 20% 30% 40% 50%

❝ 4 21.4 32.4 43.8 68.7 97.2 131

❝ 6 15.6 23.6 31.6 48.2 65.8 84.8

❝ 12 12.7 19.1 25.6 38.7 52.1 66.0

❝ 16 12.2 18.3 24.4 36.9 49.5 62.5

❝ 24 11.6 17.5 23.3 35.1 47.1 59.8

❝ 32 11.3 17.0 22.7 34.2 45.8 57.6

Uhh... Sorry about that I don't know how to interpret/use this table.

❝ For an expected CV of 20% I would say 12 subjects are OK, for HVDs the minimum in a pilot is 16-24.

O.k.. could be a good guess.

❝ Wow, four! That's brave. Six is Vinod Shah's magic number - I call that a dice game with the devil.

That's commonly used with 4-6 subjects in a BE pilot study here... I just cannot believe that the subj# like that could give a good estimation of CV_intra at all. It almost becomes SOP with local CROs here to use 4-6 subjects to perform a BE pilot study. Then they replicate the values they get from these 4-6 subjects up to 24 or so, and finally do an anova to obtain the MSE. And they get their estimated CV_intra! I am thinking that it should be very to prove that CV_intra is poorly estimated in that way.

❝ subjects each, or in two subsets of twelve subjects. Again: the bigger, the better.

Yes, but the question is: how bigger is the better? It's a pilot study only, but it seems very critical.

—
All the best,
-- Yung-jin Lee
bear v2.9.2:- created by Hsin-ya Lee & Yung-jin Lee
Kaohsiung, Taiwan https://www.pkpd168.com/bear
Download link (updated) -> here

Complete thread:

Sample Size BA/BE Sriraj 2010-02-26 14:32 [Power / Sample Size]
- Sample Size BA/BE Helmut 2010-03-01 14:00
  - Sample size for a pilot study to estimate the CVintra yjlee168 2010-03-01 19:25
    - Sample size for a pilot study to estimate the CVintra Helmut 2010-03-01 21:01
      - Sample size for a pilot study to estimate the CVintrayjlee168 2010-03-01 23:47
        
        Sample size for a pilot study to estimate the CVintra Helmut 2010-03-03 19:04
        
        Sample size for a pilot study to estimate the CVintra yjlee168 2010-03-04 22:35
      - 80% confidence ? d_labes 2010-03-19 13:02
        
        75% confidence... Helmut 2010-03-19 14:12
    - Sample size for a pilot study to estimate the CVintra ElMaestro 2010-03-01 22:23
      - Sample size for a pilot study to estimate the CVintra yjlee168 2010-03-02 00:02
      - Sample size for a pilot study to estimate the CVintra Helmut 2010-03-02 02:19
        
        Sample size for a pilot study to estimate the CVintra yjlee168 2010-03-29 13:27
        
        Sample size for a pilot study to estimate the CVintra ElMaestro 2010-03-29 13:39
        
        Sample size for a pilot study to estimate the CVintra yjlee168 2010-03-29 13:47
        
        Sequential designs (history and future) Helmut 2010-03-29 14:19
        
        Sequential designs (history and future) yjlee168 2010-03-29 19:19
        
        Sequential designs (history and future) Helmut 2010-03-29 20:43
        
        Sequential designs (history and future) yjlee168 2010-04-01 18:58
        
        Sequential designs (WinNonlin vs. bear) Helmut 2010-04-02 21:00