
222 Sample Size Calculations for Clustered and Longitudinal Outcomes
TABLE 6.10
Sample size and power for detecting a three-way interaction XZT effect δ
XZT
in model (6.38) for a 2-by-2 factorial design when randomizations occur at the
third level (two-sided significance level α = 0.05)
λ
3
r
τ
∆
XZT
ρ
1
N
1
N
2
N
(0,0)
3
Total N ϕ
XZT
1 0 0.3/4 0.1 5 8 63 10080 0.801
5 63 8 10080 0.801
0.2 5 8 56 8960 0.801
0.3/8 0.1 9 8 42 12096 0.801
0.2 9 8 38 10944 0.808
9 38 8 10944 0.808
0.1 0.3/4 0.1 5 8 133 21280 0.801
5 133 8 21280 0.801
0.2 5 8 126 20160 0.801
0.3/8 0.1 9 8 321 92448 0.801
0.2 9 8 317 91296 0.801
9 317 8 91296 0.801
1.5 0 0.3/4 0.1 5 8 48 10560 0.807
5 48 8 10560 0.807 ...