Table 1.
Arguments supplied to the gComp function in the riskCommunicator package.
Table 2.
Effect of prevalent diabetes at the beginning of the study on the 24-year risk of cardiovascular disease or death among 4,240 participants in the Framingham Heart Study.
Fig 1.
Histograms and quantile-quantile (Q-Q) plots of bootstrap iterations (R = 1000) obtained from the binary.res output for each effect measure.
NOTE: All ratio values are plotted as natural log of the actual estimate.
Fig 2.
Effect of having prevalent diabetes at the beginning of the study on the 24-year risk of cardiovascular disease or death overall and stratified by sex among 4,240 participants in the Framingham Heart Study.
A) Incidence rate ratio. B) Incidence rate difference. riskCommunicator was used to obtain marginal effect estimates (purple) and Poisson regression was used to obtain covariate-conditional estimates (green; not available for incidence rate difference). All models were adjusted for patient’s age, sex, body mass index, smoking status (current smoker or not), and prevalence of hypertension. Each point represents the point estimate and error bars show the 95% CI.