Skip to main content
. Author manuscript; available in PMC: 2017 Jul 17.
Published in final edited form as: Stat Med. 2016 Nov 2;36(4):592–605. doi: 10.1002/sim.7157

Table II.

Sample size and power calculation using the APPLE method, standard practice based on regular log-rank test (S-Logrank) and EAST software.

λ2 Consider t* Ignore t* EAST
APPLE1 Empirical power (%) S-Logrank Empirical power (%) EAST Empirical power (%)
p = 90%
0.5 274 78 205 52 400 79
0.55 357 79 267 52 500 77
0.6 475 79 356 52 670 79
0.65 649 80 486 53 900 78
0.7 922 79 691 54 1270 80
p = 80%
0.5 174 79 120 46 270 79
0.55 227 79 157 46 350 80
0.6 302 80 209 47 450 78
0.65 415 80 287 47 630 80
0.7 590 79 409 48 870 79
p = 70%
0.5 149 79 93 39 260 80
0.55 195 80 122 40 330 80
0.6 260 79 163 40 430 80
0.65 358 79 225 41 570 78
0.7 512 80 322 41 810 79
1

The sample size calculated using APPLE is based on total accrual duration A = 1 year, total study duration τ = 3 years, and Type I error rate α = 0.05.