Supplementary material: Dependent censoring bias assessment using inverse probability of censoring weights: Type 2 diabetes mellitus risk in patients initiating bisoprolol versus other antihypertensives in a Clinical Practice Research Datalink cohort study

<b>These are peer-reviewed supplementary materials for the article '</b><b>Dependent censoring bias assessment using inverse probability of censoring weights: Type 2 diabetes mellitus risk in patients initiating bisoprolol versus other antihypertensives in a Clinical Practice Research Datalink cohort study</b><b>' published in the</b><b> </b><b><i>Journal of Comparative Effectiveness Research</i></b><b>.</b><b>A.1:</b> <b>Censoring modeling</b><b>A.1.1: </b>Prior knowledge<b>A.1.2:</b> Univariate Cox model for T2DM<b>A.1.2.1: </b>Multivariate Cox model for censoring<b>Table: </b>A1<br><b>A.2:</b> Weights distribution<b>A.3:</b> Dependant censoring evaluation: IPCW Kaplan Meier curves A–E<b>A.4:</b> IPCW Cox models<b>A</b> ‒ calcium-channel blockers<b>B</b> – Diuretics vs bisoprolol<b>C</b> – Other beta blockers vs bisoprolol<br><b>A.5: </b>competing risks analysis results<b>A </b>‒ Cause-specific hazard ratios for T2DM<b>B</b> ‒ Subdistribution hazard ratios for T2DM<b>C</b> ‒ Cause-specific hazard ratios for DFM<b>D</b> ‒ Subdistribution hazard ratios for DFM