Background and Purpose-This ARISTOPHANES study (Anticoagulants for Reduction in Stroke: Observational Pooled Analysis on Health Outcomes and Experience of Patients) used multiple data sources to compare stroke/systemic embolism (SE) and major bleeding (MB) among a large number of nonvalvular atrial fibrillation patients on non-vitamin K antagonist oral anticoagulants (NOACs) or warfarin.; Methods-A retrospective observational study of nonvalvular atrial fibrillation patients initiating apixaban, dabigatran, rivaroxaban, or warfarin from January 1, 2013, to September 30, 2015, was conducted pooling Centers for Medicare and Medicaid Services Medicare data and 4 US commercial claims databases. After 1:1 NOAC-warfarin and NOAC-NOAC propensity score matching in each database, the resulting patient records were pooled. Cox models were used to evaluate the risk of stroke/SE and MB across matched cohorts.; Results-A total of 285 292 patients were included in the 6 matched cohorts: 57 929 apixaban-warfarin, 26 838 dabigatran-warfarin, 83 007 rivaroxaban-warfarin, 27 096 apixaban-dabigatran, 62 619 apixaban-rivaroxaban, and 27 538 dabigatran-rivaroxaban patient pairs. Apixaban (hazard ratio [HR], 0.61; 95% CI, 0.54-0.69), dabigatran (HR, 0.80; 95% CI, 0.68-0.94), and rivaroxaban (HR, 0.75; 95% CI, 0.69-0.82) were associated with lower rates of stroke/SE compared with warfarin. Apixaban (HR, 0.58; 95% CI, 0.54-0.62) and dabigatran (HR, 0.73; 95% CI, 0.66-0.81) had lower rates of MB, and rivaroxaban (HR, 1.07; 95% CI, 1.02-1.13) had a higher rate of MB compared with warfarin. Differences exist in rates of stroke/SE and MB across NOACs.; Conclusions-In this largest observational study to date on NOACs and warfarin, the NOACs had lower rates of stroke/SE and variable comparative rates of MB versus warfarin. The findings from this study may help inform the discussion on benefit and risk in the shared decision-making process for stroke prevention between healthcare providers and nonvalvular atrial fibrillation patients.