Air pollution effects on hospital admissions: a statistical analysis of parallel time series |
| |
Authors: | R Burnett S Bartlett D Krewski G Robert M Raad-Young |
| |
Institution: | (1) Health Canada, Environmental Health Center, Tunney's Pasture, KIA OL2 Ottawa, Canada;(2) Statistics Canada, Tunney's Pasture, RH Coats Bldg., KIA OT6 Ottawa, Canada |
| |
Abstract: | A statistical model for longitudinal count data is used to examine the potential adverse health effects of ambient air pollution. Daily respiratory admissions to 164 acute care hospitals in Ontario are obtained for the period 1983 to 1988. Estimates of ozone levels in the vicinity of each hospital are determined from air pollution monitoring stations maintained by the Ontario Ministry of the Environment. Generalized estimating equation methods are used to make inferences about the regression and overdispersion parameters. The admission data display little evidence of serial correlation and extra Poisson variation. However, admission rates vary considerably among hospitals. This latter source of variation needs to be taken into account in examining the effects of air pollution on respiratory health status. |
| |
Keywords: | Administrative health records air pollution estimating equations hospital admissions longitudinal count data overdispersion ozone serial correlation |
本文献已被 SpringerLink 等数据库收录! |