R in a Nutshell, 2nd Edition

ANOVA Test Design

If you are designing an experiment where you will be using ANOVA, you can use the power.anova.test function:

power.anova.test(groups = NULL, n = NULL,
                 between.var = NULL, within.var = NULL,
                 sig.level = 0.05, power = NULL

For this function, groups specifies the number of groups, n specifies the number of observations (per group), between.var is the variance between groups, within.var is the variance within groups, sig.level is the significance level (Type I error probability), and power is the power of the test (1 − Type II error probability). This function will calculate either groups, n, sig.level, between.var, power, within.var, or sig.level, depending on the input. You must specify exactly six of these parameters, and the remaining argument must be null; this is the value that the function calculates.