Social inequalities in residential exposure to road traffic noise: An environmental justice analysis based on the RECORD Cohort Study

Objectives To explore social inequalities in residential exposure to road traffic noise in an urban area. Methods Environmental injustice in road traffic noise exposure was investigated in Paris, France, using the RECORD Cohort Study (n=2130) and modelled noise data. Associations were assessed by estimating noise exposure within the local area around participants' residence, considering various socioeconomic variables defined at both individual and neighbourhood level, and comparing different regression models attempting or not to control for spatial autocorrelation in noise levels. Results After individual-level adjustment, participants' noise exposure increased with neighbourhood educational level and dwelling value but also with proportion of non-French citizens, suggesting seemingly contradictory findings. However, when country of citizenship was defined according to its human development level, noise exposure in fact increased and decreased with the proportions of citizens from advantaged and disadvantaged countries, respectively. These findings were consistent with those reported for the other socioeconomic characteristics, suggesting higher road traffic noise exposure in advantaged neighbourhoods. Substantial collinearity between neighbourhood explanatory variables and spatial random effects caused identifiability problems that prevented successful control for spatial autocorrelation. Conclusions Contrary to previous literature, this study shows that people living in advantaged neighbourhoods were more exposed to road traffic noise in their residential environment than their deprived counterparts. This case study demonstrates the need to systematically perform sensitivity analyses with multiple socioeconomic characteristics to avoid incorrect inferences about an environmental injustice situation and the complexity of effectively controlling for spatial autocorrelation when fixed and random components of the model are correlated.