
Sample Size Determination for Outcomes from Two-Level Trials 179
TABLE 5.9
Sample size and statistical power for detecting a main effect |p
1
−p
0
| on binary
outcome in model with m = 2 (5.34) when randomizations occur at the second
level (two-sided significance level α = 0.05)
λ p
0
p
1
ρ N
1
N
(0)
2
Total N ϕ
1 0.4 0.6 0.1 10 19 380 0.812
20 15 600 0.826
0.2 10 28 560 0.812
20 24 960 0.812
0.7 0.1 10 8 160 0.801
20 7 280 0.854
0.2 10 12 240 0.808
20 11 440 0.834
1.5 0.4 0.5 0.1 10 16 400 0.817
20 12 600 0.810
0.2 10 23 575 0.807
20 20 100 0.813
0.6 0.1 10 7 175 0.823
20 6 300 0.865
0.2 10 10 250 0.811
20 9 450 0.830
Note: λ represents the ratio of the number of level 2 units ...