The relationship between dietary fat intake and breast cancer incidence was examined in the National Health and Nutrition Examination Survey I (NHANES I) Epidemiologic Follow-up Study cohort. This cohort is derived from adults (greater than or equal to 25 yr) examined in the NHANES I (1970-75) cross-sectional survey of the U.S. population and provides a mean follow-up time of 10 years. An analytic sample of 5,485 women, including 99 breast cancer cases (34 premenopausal and 65 postmenopausal at NHANES I baseline), was examined for associations with dietary intake of fat, percent energy from fat, total energy, saturated fat, polyunsaturated fat, monounsaturated fat, and cholesterol on the basis of a 24-hour recall administered at the baseline NHANES I examination. No significant differences in dietary fat intake between cases and noncases were evident when mean intakes for each group were compared. For total fat (g) and saturated fat (g), a significant inverse association was indicated in proportional hazards analyses. Adjustment of fat for total energy intake resulted in a smaller effect that was no longer statistically significant. Adjustment for accepted breast cancer risk factors did not change these findings. This prospective study of a sample from the U.S. population does not support the hypothesis that high dietary fat intake increases breast cancer risk. Indeed, some lower risk associated with high fat intake may be indicated, although this result may be influenced by methodologic problems with the dietary assessment.