To determine if age-related hearing loss is associated with social isolation and whether factors such as age, gender, income, race, or hearing aid use moderated the association. Cross-sectional. Randomly sampled United States communities. Cross-sectional data on adults 60 to 84 years old from the 1999 to 2006 cycles of the National Health and Nutrition Examination Survey were analyzed. The dependent variable was social isolation, which was defined using the social isolation score (SIS), a 4-point composite index consisting of items pertaining to strength of social network and support. SIS scores ≥2 were considered indicative of social isolation. The independent (predictor) variable was the pure tone average of speech frequency (0.5-4 kHz) hearing thresholds in the better-hearing ear. Covariates included potential medical, demographic, and otologic confounders. We used multivariate logistic regression to evaluate the association between hearing loss and the odds of having social isolation. An exploratory analysis was performed to assess the strength of associations between hearing loss and individual items of the SIS scale. Greater hearing loss was associated with increased odds of social isolation in women aged 60 to 69 years (odds ratio OR, 3.49 per 25-dB of hearing loss; 95% confidence interval, 1.91, 6.39; P < .001). Effect modification by gender was significant in this age group (P = .003). Hearing loss was not significantly associated with social isolation in other age and gender groups. Greater hearing loss is associated with increased odds of being social isolated in a nationally representative sample of women aged 60 to 69 years.