Rで検定力分析

分散分析の検定力分析をRで行うことができる。
power.anova.test()
を利用。exampleを見ればわかりやすいだろう。

> example(power.anova.test)

pwr.n.> power.anova.test(groups=4, n=5, between.var=1, within.var=3)

Balanced one-way analysis of variance power calculation

groups = 4
n = 5
between.var = 1
within.var = 3
sig.level = 0.05
power = 0.3535594

NOTE: n is number in each group


pwr.n.> # Power = 0.3535594
pwr.n.>
pwr.n.> power.anova.test(groups=4, between.var=1, within.var=3,
pwr.n.+ power=.80)

Balanced one-way analysis of variance power calculation

groups = 4
n = 11.92613
between.var = 1
within.var = 3
sig.level = 0.05
power = 0.8

NOTE: n is number in each group


pwr.n.> # n = 11.92613
pwr.n.>
pwr.n.> ## Assume we have prior knowledge of the group means:
pwr.n.> groupmeans <- c(120, 130, 140, 150)

pwr.n.> power.anova.test(groups = length(groupmeans),
pwr.n.+ between.var=var(groupmeans),
pwr.n.+ within.var=500, power=.90) # n = 15.18834

Balanced one-way analysis of variance power calculation

groups = 4
n = 15.18834
between.var = 166.6667
within.var = 500
sig.level = 0.05
power = 0.9

NOTE: n is number in each group

>

２番目の例は、必要なサンプルの大きさを求めるもの。
詳しくは、
> help(power.anova.test)