Sample size graphs for "proving the null hypothesis".

摘要: Abstract Sample size graphs are given for clinical trials designed to test whether an experimental therapy is as effective a standard therapy. We assume dichotomous outcome variable and one-sided of the hypothesis that probability success with greater than by at least some specified amount δ. Graphs significance level α = 0.01, 0.025, 0.05; type II error β 0.10, 0.20; δ 0.20.