Fig. 3
From: More efficient and inclusive time-to-event trials with covariate adjustment: a simulation study
Effect of broader eligibility criteria and of covariate adjustment on statistical power. Different inclusion statuses are shown by color and adjustment statuses by type of line, irrespective of color. (A) Results of the parametric simulations where the covariate adjusted for is a standard Gaussian. (B) Results of the semi-synthetic simulations based on the HCC-TCGA cohort. The clinical covariates adjusted for are ECOG score and tumor staging. The three levels of inclusion are based on eligibility criteria of past and ongoing trials outlined in Table 1. For all simulations, a constant treatment effect size is assumed across the population. More restrictive eligibility criteria exclude patients with higher disease severity