Abstract Background A low ankle-brachial index (ABI) is associated with increased risk of coronary heart disease, stroke, and death. Regression model parameter estimates may be biased due to measurement error when the ABI is included as a predictor in regression models, but may be corrected if the reliability coefficient, R, is known. The R for the ABI computed from DINAMAP™ readings of the ankle and brachial SBP is not known. Methods A total of 119 participants in both the Atherosclerosis Risk in Communities (ARIC) study and the NHLBI Family Heart Study (FHS) had repeat ABIs taken within 1 year, using a common protocol, automated oscillometric blood pressure measurement devices, and technician pool. Results The estimated reliability coefficient for the ankle systolic blood pressure (SBP) was 0.68 (95% CI: 0.57, 0.77) and for the brachial SBP was 0.74 (95% CI: 0.62, 0.83). The reliability for the ABI based on single ankle and arm SBPs was 0.61 (95% CI: 0.50, 0.70) and the reliability of the ABI computed as the ratio of the average of two ankle SBPs to two arm SBPs was estimated from simulated data as 0.70. Conclusion These reliability estimates may be used to obtain unbiased parameter estimates if the ABI is included in regression models. Our results suggest the need for repeated measures of the ABI in clinical practice, preferably within visits and also over time, before diagnosing peripheral artery disease and before making therapeutic decisions.