In planning experiments having two groups of equal but small size, inv
estigators face the uncertainty of power calculations that rely on asy
mptotic methods. This paper presents a method for determining power fo
r two-sided tests. I compare two randomization tests, Fisher's exact t
est (FET), and the mid-P (MID), with the uncorrected chi-square test (
CHI). Results show power as a function of relative risk for these meth
ods, and assesses their relative power and type I error rates. MID is
shown to have intermediate power between CHI, which is the most powerf
ul, and FET, the least powerful. Situations are shown in which CHI and
MID occasionally exceed the nominal level of alpha.