Two basic kinds of observational epidemiological studies have been conducted to determine risks associated with air pollution: descriptive (such as ecological studies) and analytical (such as: cross-sectional, case-control, and cohort studies) (Table 9-1). These two study approaches differ primarily in the supportive evidence they provide about a possible causal association. Unlike an analytical study, an Ecological Study does not link individual outcome events to the individual exposure or confounding characteristics, and it does not link individual exposure and confounding characteristics with one another. In an ecological study, information about exposure and disease is available only for groups of people, and critical information can be lost in the process of aggregating these data. Results from ecological studies are diffi cult to interpret, and serious errors may occur when it is assumed that inferences from an ecological analysis pertain either to the individuals within the group or to individuals across the groups. In the time series analysis, associations between air pollution metrics and morbidity or mortality are analysed. Log-linear regression models express the expected total number of events on each day as a function of the exposure level and potential confounding variables.