Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: Extension of a conditional performance score for sample size recalculation rules to the setting of binary endpoints

Fig. 1

Global power and mean sample size for the considered recalculation rules for binary endpoints in the main simulation. The red dashed line represents the sample size and power for a fixed design with a target power of 80% for an assumed \(\lambda =0.3\). The proportion in the control group is set to \(p_{C}=0.3\) and the first stage sample size is set to \(n_{1}=50\). The global significance level \(\alpha = 0.025\), efficacy stopping boundaries were chosen according to Pocock [15] and the binding futility stopping bound is set to \(\alpha _{0}=0.5\). The maximum sample size is set to \(n_{max} = 200\). OCP: Observed conditional power approach; restrOCP: Restricted observed conditional power approach; Promising: Promising zone approach; OptFunc: Optimization function approach; classicGS: group sequential approach

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us