R function for calculating A/B testing sample size from Ian Clarke(of 37signals)'s

gistfile1.r

# ref: http://37signals.com/svn/posts/3004-ab-testing-tech-note-determining-sample-size
#
# p1 = Variable A results. e.g. conversion rate from test A
# p2 = Variable B results
# power = chance of false negative (A power of 0.80 means that there is an 80% chance that if there was an effect, we would detect it )
# sig.level = chance of false positive (0.05 = 5%)

power.prop.test(p1=0.1, p2=0.11, power=0.8, alternative='two.sided', sig.level=0.05)

# Output will be a number signifying minimal sample size that meets the above criteria

Thanks for uploading this Zach!