Skip to main content
Fig. 3 | BMC Medical Research Methodology

Fig. 3

From: Evaluating antimalarial efficacy in single-armed and comparative drug trials using competing risk survival analysis: a simulation study

Fig. 3

Overestimation of failure using K-M method compared to the CIF in simulation study I (n = 500 subjects). The overestimation \( \left({\widehat{F}}_{KM}(t)-{\widehat{F}}_{CIF}(t)\right) \) of cumulative recrudescence by the K-M method. Each panel represents different underlying status of drug efficacy on average (~ 5, 10 and 15% recrudescence observed) in a study with a sample size of 500 subjects/trial. The results are presented from 1000 independent simulation runs. The variation in absolute overestimation within each boxplot is due to varying proportion of new infection observed within the simulation scenario. Within each panel, the colours indicate different simulated scenarios of proportions of new infections: < 10% new infections (grey), 10–20% new infections (blue), 20–40% new infections (green) and > 40% new infections (orange), representing areas of progressively increasing malaria transmission from very low to very high

Back to article page