OBJECTIVE - To examine the associations between reported intakes of dietary fat and incident type 2 diabetes. RESEARCH DESIGN AND METHODS - We studied the relation between dietary fatty acids and diabetes in a prospective cohort study of 35,988 older women who initially did not have diabetes. Diet was assessed with a food frequency questionnaire at baseline, and 1,890 incident cases of diabetes occurred during 11 years of follow-up. RESULTS - After adjusting for age, smoking, alcohol consumption, BMI, waist-to-hip ratio, physical activity, demographic factors, and dietary magnesium and cereal fiber, diabetes incidence was negatively associated with dietary polyunsaturated fatty acids, vegetable fat, and trans fatty acids and positively associated with ω-3 fatty acids, cholesterol, and the Keys score. After simultaneous adjustment for other dietary fat, only vegetable fat remained clearly related to diabetes risk. Relative risks across quintiles of vegetable fat intake were 1.00, 0.90, 0.87, 0.84, and 0.82 (P = 0.02). Diabetes risk was also inversely related to substituting polyunsaturated fatty acids for saturated fatty acids and positively correlated to the Keys dietary score. CONCLUSIONS - These data support an inverse relation between incident type 2 diabetes and vegetable fat and substituting polyunsaturated fatty acids for saturated fatty acids and cholesterol.