Hello,
The current common practice helps to avoid all but 1/24 (4.16%) of an adverse event.
We're trying to show that another, easier practice will not have worse outcomes.
Thus, I'm trying to find the sufficient sample size, to achieve statistical power. I tried this calculator:
http://powerandsamplesize.com/Calculators/Compare-2-Proportions/2-Sample-Non-Inferiority-or-Superiority
But I'm not sure about which values should I enter for P-B (proportions for the experiment group) or for the non-inferiority margin.
Since no previous data regarding this question was collected, should we start with a preliminary just to clarify the proportions in the new suggested practice first?
Every help would be appreciated! Thank you
pl get the calculation from the link
https://www2.ccrb.cuhk.edu.hk/stat/proportion/tspp_sup.htm
Ajit kumar Roy
Thanks. But what do I fill in for the proportions of the seconds group and the non-inferiority margin, if I do not know the proportions of the second group yet?
Dear Uri
You can use G*Power software to estimate the suitable sample size for wide range of experiments (including your question).
G*Power is free to download and easy to use after reading the manual, the download link:
http://download.cnet.com/G-Power/3000-2054_4-10647044.html
The link to download G*Power manual:
http://www.gpower.hhu.de/fileadmin/redaktion/Fakultaeten/Mathematisch-Naturwissenschaftliche_Fakultaet/Psychologie/AAP/gpower/GPowerManual.pdf
I hope that be useful for you.
Good Luck
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size