Recent reports suggest that obesity, or conditions associated with obesity, might be risk factors for non-Hodgkin lymphoma (NHL), a cancer with dramatically increasing incidence in western countries over the last several decades. Physical inactivity increases the risk of obesity and of type 2 diabetes, but there are few data on the association of physical activity with risk of NHL. We evaluated these factors in a population-based case-control study conducted in Detroit, Iowa, Los Angeles, and Seattle from 1998 to 2000. Incident HIV-negative NHL cases aged 20-74 years were rapidly reported in each area (n = 1321). Controls were identified through random digit dialing and Medicare files, and were frequency matched to cases on sex, age, race, and study site (n = 1057). Risk factor data were collected by in-person interviews and self-administered questionnaires. Unconditional logistic regression was used to estimate the odds ratio (OR) and 95% confidence intervals (CI), adjusted for age, sex, race and study center. High body mass index (OR = 1.73 for 35+ versus <25 kg/m2; 95% CI 1.15-2.59) and history of gallstones (OR = 1.95, 95% CI 1.11-3.40) were positively associated with diffuse NHL, but were not associated with follicular or all NHL combined. Height was positively associated with risk of all NHL combined (OR = 1.38 for >70 versus <65 inches; 95% CI 0.98-1.94), and positive associations were apparent for both diffuse and follicular NHL. Non-occupational physical activity was inversely associated with risk of all NHL combined (ORs with increasing level: 1, 0.75, 0.71, 0.55, 0.68; p-trend = 0.04) and for diffuse and follicular NHL. We observed no association of total energy intake, type 2 diabetes, or hypertension with risk of NHL. In a multivariable model to predict risk of diffuse NHL, BMI (OR = 2.15 for 35+ versus <25 kg/m2; 95% CI 1.09-4.25) and height (OR = 1.63 for 71+ versus <65 inches; 95% CI 0.75-3.57) were positively associated with risk while physical activity was weakly and inversely associated risk (ORs with increasing level: 1, 0.76, 0.72, 0.78, 0.82; p-trend = 0.9). BMI and history of gallstones were positively associated with risk of diffuse NHL, supporting a role for obesity in this NHL subtype. Height was positively associated with NHL risk across subtypes, and suggests a role for early life nutrition in NHL risk. Non-occupational physical activity was only weakly and inversely associated with NHL risk after adjustment for obesity, height and alcohol use.