Effect modification by community characteristics on the short-term effects of ozone exposure and mortality in 98 US communities

Abstract

Previous research provided evidence of an association between short-term exposure to ozone and mortality risk and of heterogeneity in the risk across communities. The authors investigated whether this heterogeneity can be explained by community-specific characteristics: race, income, education, urbanization, transportation use, particulate matter and ozone levels, number of ozone monitors, weather, and use of air conditioning. Their study included data on 98 US urban communities for 1987 to 2000 from the National Morbidity, Mortality, and Air Pollution Study; US Census; and American Housing Survey. On average across the communities, a 10-ppb increase in the previous week's ozone level was associated with a 0.52% (95% posterior interval: 0.28, 0.77) increase in mortality. The authors found that community-level characteristics modify the relation between ozone and mortality. Higher effect estimates were associated with higher unemployment, fraction of the Black/African-American population, and public transportation use and with lower temperatures or prevalence of central air conditioning. These differences may relate to underlying health status, differences in exposure, or other factors. Results show that some segments of the population may face higher health burdens of ozone pollution.

Figure 1

Communities' maximum likelihood estimates and community-specific characteristics for unemployment, race, long-term temperature, public transportation, and central air conditioning (AC), United States, 1987–2000. The size of each circle corresponds to the inverse of the standard error of the community's maximum likelihood estimate; that is, larger circles represent more certain estimates. The bold line reflects results from the univariate second-stage analysis in which the Bayesian hierarchical model was used. Long-term temperature (°C = (°F − 32) × 5/9) included only those days for which ozone data were available. L06, ozone during the previous week (lag 0 days, lag 1 day, lag 2 days … 6 days previous).