Fig. 3
From: Overestimation of benefit when clinical trials stop early: a simulation study
Absolute overestimate of the relative risk reduction as a function of the number of observed events and the observed relative risk reduction in simulated typical truncated trials. Data are a “heatmap” of the absolute overestimate of the relative risk reduction showing all cells for which there were at least 50 simulated trials. The range over which data is displayed is the range over which our model predictions can be applied.