Skip to main content

Table 3 Risk of coronary heart diseases in the MEGA study at 5 years after randomization

From: Doubly robust estimator of risk in the presence of censoring dependent on time-varying covariates: application to a primary prevention trial for coronary events with pravastatin

  Diet group Diet + pravastatin group  
Method Risk (%) 95% CI Risk (%) 95% CI Risk Ratio 95% CI
Kaplan–Meiera 2.34 (1.90, 2.89) 1.63 (1.26, 2.11)   
IPCW Kaplan–Meier 2.39 (1.91, 2.95) 1.60 (1.19, 2.10) 0.68 (0.40, 1.06)
Parametric g-formula 2.36 (1.97, 3.01) 1.66 (1.30, 2.05) 0.71 (0.47, 0.98)
Proposed estimator 2.38 (1.91, 2.95) 1.61 (1.22, 2.06) 0.69 (0.42, 1.03)
  1. CI confidence interval
  2. aThe confidence intervals of the Kaplan–Meier estimator was obtained using the Greenwood formula