摘要：Using an ecological study design, Gordon et al. (Isr J Health Policy Res 6:39, 2017) demonstrate variations in mortality patterns across districts and sub-districts of Israel during 2008–2013. Unlike other epidemiological study designs, the units of analysis in ecological studies are groups of people, often defined geographically, and the exposures and outcomes are aggregated, and often known only at the population-level. The ecologic study has several appealing characteristics (such as reliance on public-domain anonymous data) alongside a number of important potential limitations including the often mentioned ‘ecological fallacy’. Advantages and disadvantages of the ecological design are described briefly below.
