Simulations? [Power / Sample Size]

posted by mittyri – Russia, 2019-01-31 23:28 (606 d 18:17 ago) – Posting: # 19836
Views: 1,283

Hi,

if you don't have analytical solution - look for simulations approach :-D
Simulate the data using known distribution parameters, desired sample size and then use bootstrap technique for evaluation. Repeat it ad-hoc (until the success/failure ratio stabilizes). Then change the sample size and repeat until desired power is reached. Don't forget about SciAdv.

Kind regards,
Mittyri

Complete thread:

Activity
 Admin contact
21,086 posts in 4,398 threads, 1,468 registered users;
online 9 (1 registered, 8 guests [including 3 identified bots]).
Forum time: Tuesday 18:46 CEST (Europe/Vienna)

To know the history of science is to recognize the mortality
of any claim to universal truth.    Evelyn Fox Keller

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5