Fig. 7From: Generating high-fidelity synthetic time-to-event datasets to improve data transparency and accessibilityKaplan–Meier estimates with marginal predictions in the corresponding population subgroups (Subsite: Sigmoid; Age Group: Over 75; Stage: Distant; Sex: Female), where covariate distributions are modelled in different orders. Ascending Order: Sex, Stage, Subsite, Year of Diagnosis; Descending Order: Year of Diagnosis, Subsite, Stage, Sex; Chosen Order: Year of Diagnosis, Stage, Sex, Subsite)Back to article page