Background: Atrial fibrillation (AF) significantly increases the risk of stroke and disease burden; it is an established predictor of poor outcomes after stroke. However, reported differences in outcomes after stroke among elderly patients between AF and non-AF group are conflicting. We aimed to compare differences in outcomes at 1 year and 3 years after stroke among elderly patients (aged >= 75 years old) between AF group and non-AF group. Methods: We recruited 1070 consecutive elderly patients who experienced acute ischemic stroke between January 2008 and December 2013 in Jiamusi University First Hospital, China in this study. Information regarding stroke subtype, severity, risk factors, and outcome (mortality, dependency, and recurrence) at 3 and 12 months after stroke were recorded and assessed between AF group and non-AF group. Results: The prevalence of AF was 16.1% overall, with a similar trend in the prevalence of AF between men and women. The AF group were more likely to experience severe stroke compared to the non-AF group (32.0 vs. 11.9%, respectively; P < 0.001). There were no obvious differences between groups regarding the prevalence of hypertension, dyslipidemia, obesity, current smoking, and alcohol drinking but there was a higher prevalence of diabetes in the non-AF group (20.3 vs. 30.1%, P = 0.010). Mortality and dependency rates were significantly higher in the AF group than in the non-AF group at 1 year after stroke (29.6 vs. 17.8%, P = 0.001 for mortality; and 59.5 vs. 36.1%, P = 0.010 for dependency) and 3 years after stroke (46.1 vs. 33.2%, P = 0.032 for mortality; and 70.7 vs. 49.2%, P = 0.010 for dependency); however, there was no significant between-groups differences in rates of recurrence across the follow-up periods. The results for dependency remained stable after adjustment for sex, stroke severity, and stroke risk factors at 3 years after stroke (OR, 2.26; 95% Cl, 1.06-4.81; P = 0.034); however, the relationship between AF and mortality and recurrence disappeared after adjusting for these covariates Conclusion: These findings suggest that it is crucial to highlight the treatment of elderly stroke patients with AF in order to reduce poor outcomes among the elderly and to reduce the burden of AF in China.