Panel A shows the relationship between the annual incidence rate of an event in the control group and the required sample size for a 5-year clinical trial that has a 90% probability or power to detect a 20% reduction of the event rate in the treatment group. Panel B shows the probability of detecting this same 20% difference (i.e., the power) for different incidence rates in the control group if the trial’s sample size is fixed at 10,000.