Longitudinal association between density of retail food stores and body mass index in Mexican school children and adolescents

Abstract

Background: Obesity is rapidly increasing in Mexican children and adolescents, while food environments are rapidly changing. We evaluated the association between changes in retail food stores and change in body mass index (BMI) in Mexican children and adolescents.

Methods: Data on 7507 participants aged 5-19 years old came from the Mexican Family Life Survey 2002-2012. Density of food stores at the municipal-level (number of food stores/area in km²) came from the Economic Censuses of 1999, 2004 and 2009. We categorized food stores as small food retail (small neighborhood stores, tiendas de abarrotes in Mexico), specialty foods, fruit/vegetables, convenience foods, and supermarkets. Associations between change in food stores and change in BMI were estimated using five longitudinal linear fixed-effects regression models (one per type of food store) adjusted for age, parental education, municipal-level socioeconomic deprivation and population density. Density of each food store type was operationalized as quartiles. Analyses were stratified by urbanization.

Results: There was an inverse dose-response association between increases in fruit/vegetable store density and BMI (β = -0.455 kg/m², β = -0.733 kg/m², and β = -0.838 kg/m² in the second, third, and fourth quartile). In non-urban areas, children living in municipalities with the highest density of small food retail stores experienced a reduction in BMI (β = -0.840 kg/m²). In urban areas, there was an inverse association between specialty food stores with BMI (β = -0.789 kg/m² in third quartile, and β = -1.204 kg/m² in fourth quartile). We observed dynamic associations with age; results suggested stronger associations in adolescents.

Conclusions: The availability of fruit/vegetable stores may influence a reduction in children and adolescents BMI. These results indicate that policy approaches could be tailored by type of food store - with some consideration for level of urbanization and children's age.

Fig. 1. Flowchart of the study sample.

MxFLS-1 the Mexican Family Life Survey wave 1 (2002); MxFLS-2 the Mexican Family Life Survey wave 2 (2005–2006); MxFLS-3 the Mexican Family Life Survey wave 3 (2009–2012); BMI Body mass index.