Does adding tourniquet decrease mortality in pocine model of cardiac arrest ressucitation?
From a previous study, survival in this model is 24/33 to 18/31. (Ewy, Gordon A., et al. “Improved neurological outcome with continuous chest compressions compared with 30: 2 compressions-to-ventilations cardiopulmonary resuscitation in a realistic swine model of out-of-hospital cardiac arrest.” Circulation 116.22 (2007): 2525-2530.)
The alpha level for this study will be 0.05, a power of 80% (thus, a beta of 1-0.8=0.2).
The proportion between groups can be 1:1 because its an experimental model.
It is a superiority study because adding tourniquet increases workload.
The margin is zero because it is a superiority study.
The proposed relative risk reduction is to 40% of predicted risk (60% relative risk reduction)
rrr=0.4
alpha=0.05
beta=0.2
p1=(24+18)/(33+31)
p2=rrr*p1
k=1:1
delta=p1-p2
margin=0
print(TwoSampleProportion.NIS(alpha,beta,p1,p2,k,delta,margin))## [1] 16.7158Therefore, 17 pigs on each group will be necessary.