Validation of secondary data sources of the retail food environment in the capital of Uruguay, an emerging Latin American country.

Secondary data sources are frequently used for characterizing physical access to food. Although several studies have reported that they tend to show a moderate agreement with field observation in WEIRD (Western Educated Industrialized Rich and Democratic) countries, little is known about their validity in non-WEIRD countries. The aim of the present research was to assess the validity of secondary data sources of the retail food environment in Montevideo, the capital of Uruguay, an emerging Latin American country. A random sample of 106 census tracts was obtained, covering 12% (62 km) of the city's total area. Two secondary data sources were considered: administrative records and Google Maps. An aggregate database was created by manually removing duplicates. A total of 1051 unique outlets were listed in the database within the census tracts included in the sample. Field validation was performed by six teams of two observers. A total of 1200 food outlets were identified on the ground, including 463 (38.6%) outlets not listed on any database. On the contrary, 297 outlets listed in the databases (28.3%) were not found or were closed at the time of field validation. At the aggregate level, sensitivity and concordance were moderate (0.614 and 0.487, respectively), whereas positive predictive value was substantial (0.701). However, large heterogeneity in the validity of the database across census tracts was found. Sensitivity, positive predictive value, and concordance were positively associated with the socio-economic status index of the census tract. These results suggest that secondary data sources must be used with caution, particularly for the characterization of areas with low socio-economic status.