Skip to main content
. 2019 Dec 10;85(1):101–120. doi: 10.1007/s11336-019-09692-3

Table 1.

Computed sample size, estimated power, and simulated power for the ANOVA, approximate ANCOVA, and exact ANCOVA methods when G=3, σY2=10000, ρ=0.1, σ2=9900, {μ1,μ2,μ3}={400,450,500}, δ2=0.1684, Type I error α=0.05, and nominal power 1-β=0.80

P ANOVA Approximate ANCOVA Exact ANCOVA
NTO Estimated power Simulated power Error NTA Estimated power Simulated power Error NTE Estimated power Simulated power Error
1 63 0.8148 0.8169 - 0.0021 63 0.8185 0.8158 0.0027 63 0.8115 0.8123 - 0.0008
2 63 0.8148 0.8062 0.0086 63 0.8181 0.7993 0.0188 63 0.8038 0.7995 0.0043
3 63 0.8148 0.8014 0.0134 63 0.8178 0.7922 0.0256 66 0.8176 0.8216 - 0.0040
4 63 0.8148 0.7913 0.0235 63 0.8174 0.7874 0.0300 66 0.8104 0.8094 0.0010
5 63 0.8148 0.7795 0.0353 63 0.8170 0.7796 0.0374 66 0.8029 0.8026 0.0003
6 63 0.8148 0.7703 0.0445 63 0.8166 0.7773 0.0393 69 0.8166 0.8185 - 0.0019
7 63 0.8148 0.7671 0.0477 63 0.8161 0.7622 0.0539 69 0.8093 0.8080 0.0013
8 63 0.8148 0.7516 0.0632 63 0.8157 0.7522 0.0635 69 0.8018 0.8038 - 0.0020
9 63 0.8148 0.7412 0.0736 63 0.8152 0.7476 0.0676 72 0.8156 0.8210 - 0.0054
10 63 0.8148 0.7355 0.0793 63 0.8147 0.7302 0.0845 72 0.8083 0.8049 0.0034