Figure 2

Hypothetical trial: effect on all-cause mortality is a weighted average of effect on cause-specific mortality. The treatment reduces the risk of death due to bleeding by one third (RR = 0.67) but has no effect on other causes of death (RR = 1.0). The effect on all-cause mortality (RR = 0.8) is a weighted average of its effect on deaths due to bleeding and on other causes of death, weighted according to the relative contributions of the different causes.