Area-aggregated assessments of perceived environmental attributes may overcome single-source bias in studies of green environments and health: results from a cross-sectional survey in southern Sweden

Background: Most studies assessing health effects of neighborhood characteristics either use self-reports or objective assessments of the environment, the latter often based on Geographical Information Systems (GIS). While objective measures require detailed landscape data, self-assessments may yield confounded results. In this study we demonstrate how self-assessments of green neighborhood environments aggregated to narrow area units may serve as an appealing compromise between objective measures and individual self-assessments. Methods: The study uses cross-sectional data (N = 24,847) from a public health survey conducted in the county of Scania, southern Sweden, in 2008 and validates the Scania Green Score (SGS), a new index comprising five self-reported green neighborhood qualities (Culture, Lush, Serene, Spacious and Wild). The same qualities were also assessed objectively using landscape data and GIS. A multilevel (ecometric) model was used to aggregate individual self-reports to assessments of perceived green environmental attributes for areas of 1,000 square meters. We assessed convergent and concurrent validity for self-assessments of the five items separately and for the sum score, individually and area-aggregated. Results: Correlations between the index scores based on self-assessments and the corresponding objective assessments were clearly present, indicating convergent validity, but the agreement was low. The correlation was even more evident for the area-aggregated SGS. All three scores (individual SGS, area-aggregated SGS and GIS index score) were associated with neighborhood satisfaction, indicating concurrent validity. However, while individual SGS was associated with vitality, this association was not present for aggregated SGS and the GIS-index score, suggesting confounding (single-source bias) when individual SGS was used. Conclusions: Perceived and objectively assessed qualities of the green neighborhood environment correlate but do not agree. An index score based on self-reports but aggregated to narrow area units can be a valid approach to assess perceived green neighborhood qualities in settings where objective assessments are not possible or feasible.