α 0.05 [Power / Sample Size]

posted by arl_stat – India, 2020-06-11 08:15 (103 d 05:01 ago) – Posting: # 21526
Views: 1,612

Many thanks Sir. :-)

Page no. 10 of 12 of the article for full replicate study, captures the below table:
Table A2. Sample sizes for the requirements of EMA in 4-period studies
80% POWER
CV  GMR  0.85  0.90  0.95  1.00  1.05  1.10  1.15  1.20
30%       127    35    19    15    18    30    68  >201


I tried calculating the above sample size using the below SAS code but the output did not match.
%let CV=0.30;
proc power;
   TwoSampleMeans Test = Equiv_Mult
      Lower = 0.8
      Upper = 1.25
      Alpha = 0.05
      MeanRatio =  0.85 0.90 0.95
      CV = &CV.
      Power = 0.80  0.90
      NPerGroup = .
   ;
  run;
Output:
Fixed Scenario Elements
Distribution  Lognormal
Method  Exact
Lower Equivalence Bound  0.8
Upper Equivalence Bound  1.25
Alpha  0.05
Coefficient of Variation  0.3


Computed N per Group
Index  Mean Ratio  Nominal Power  Actual Power  N per Group
1         0.85          0.8           0.8           291
2         0.85          0.9           0.9           403
3         0.9           0.8           0.802          78
4         0.9           0.9           0.902         108
5         0.95          0.8           0.803          38
6         0.95          0.9           0.901          51


Please guide.

Thanks in advance.


Edit: Tabulators changed to spaces and BBcoded. Code and results BBCoded; see also this post #6. [Helmut]

Complete thread:

Activity
 Admin contact
21,069 posts in 4,392 threads, 1,467 registered users;
online 12 (1 registered, 11 guests [including 3 identified bots]).
Forum time: Tuesday 13:16 CEST (Europe/Vienna)

Everybody is a Bayesian.
It’s just that some know it, and some don’t.    Trivellore Raghunathan

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