Methodological issues in studies of air pollution and daily counts of deaths or hospital admissions

摘要: STUDY OBJECTIVE: To review the issues and methodologies in epidemiologic time series studies of daily counts mortality hospital admissions illustrate some methodologies. DESIGN: This is a paper with an example drawn from elderly Cleveland, Ohio, USA. MAIN RESULTS: The central issue control for seasonality. Both over under are possible, use diagnostics, including plots, necessary. Weather dependence probably non-linear, adequate methods necessary to adjust this. In categorical variables weather sinusoidal terms filtering season illustrated. After season, weather, day week effects, admission persons aged 65 older Cleveland respiratory illness was associated ozone (RR = 1.09, 95% CI 1.02, 1.16) particulates (PM10 1.12, 1.01, 1.24), marginally sulphur dioxide (SO2) 1.03, 0.99, 1.06). All relative risks 100 micrograms/m3 increase pollutant. CONCLUSIONS: Several exist seasonality while examining associations between air pollution morbidity. each case, care judgement required.