Fig. 2From: Interpretation of active-control randomised trials: the case for a new analytical perspective involving averted eventsSensitivity analyses of DISCOVER data. Top panel: Varying counterfactual placebo incidence. Lower panel: Varying counterfactual effectiveness of TDF-FTC. Black line, point estimate. Grey lines, 2.5% and 97.5% confidence limits. Note different scales on graphs. Methods for deriving confidence limits are given in references 21 and 22Back to article page