Skip to main content
Fig. 2 | BMC Medical Research Methodology

Fig. 2

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

Fig. 2

Comparison of the conditional performance score (CPS) values between normally distributed endpoints (left panel) and binary endpoints (right panel) for the considered sample size recalculation rules in the main simulation. Score values are printed for \(\Delta ,\lambda \in \{0,0.1,0.2,0.3,0.35,0.4,0.5,0.6\}\). The first stage sample size is set to \(n_{1}=50\), the maximum sample size is set to \(n_{max}=200\) with global one-sided significance level \(\alpha = 0.025\), efficacy stopping boundaries were chosen according to Pocock [15] and binding futility stopping bound represented by \(\alpha _{0}=0.5\). 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