The relationship between dietary intake and obesity is complex, and dietary pattern analysis may offer new insight. We examined associations between dietary patterns identified in a diverse cohort of adolescents and weight status cross-sectionally and over a 5-year period. Project EAT (Eating Among Teens) (Time 1) collected data on 4746 middle (younger cohort) and high school (older cohort) students in 1998-9. EAT-II (Time 2) resurveyed 2516 of the original cohort in 2003-4. All analyses were run separately by age cohort and sex. The relationship between dietary patterns identified previously (vegetable, fruit, vegetable & fruit, starchy food, sweet & salty snack food, and fast food) and weight status was examined using logistic regression. All analyses were adjusted for socioeconomic status, race/ethnicity and activity level (longitudinal analyses were also adjusted for baseline weight status). In cross-sectional analyses, higher adherence to dietary patterns loading heavily on vegetables was associated with lower risk of overweight/obese weight status in older and younger girls, whereas higher adherence to a 'sweet & salty snack food' pattern was associated with lower risk in older and younger boys. These associations were found prospectively in older boys and girls, but were no longer significant in analyses adjusting for baseline weight status. We did not find consistent or intuitive associations between dietary patterns and weight status. Identified patterns may not capture the elements of diet that are truly important in determining adolescent weight, or diet may not be the primary driver in determining weight status at this age. Methodological difficulties in assessing diet must also be taken into consideration.