Fig. 2
From: More efficient and inclusive time-to-event trials with covariate adjustment: a simulation study
Reduction in sample size \({R}_{\mathsf{o}\mathsf{b}\mathsf{s}}^{2}\) as a function of the prognostic performance (C-index) of the covariate for a range of cumulative incidence values. Cumulative incidence \(\Lambda\) is measured at the end of the follow-up period. In the simulations, the hazard ratio is set at \(\theta =0.7,\) the drop-out rate at \(d=0.01\), and the shape parameter of the Weibull distribution at \(w=1.5\). The cumulative incidence values that are provided for the breast cancer and HCC indications come from clinical trials selected in Table 2. eBC, early breast cancer; eHCC, early resectable hepatocellular carcinoma; mBC, metastatic breast cancer; aHCC, advanced hepatocellular carcinoma