[The assessment of disease risk in the proximity of a source of environmental pollution: a review].

An increasingly common public health problem is the perception that disease incidence has increased or a cluster of disease has occurred in a community. In most cases, a local factor (e.g. the location of a nuclear installation) is hypothesized to be associated with the disease. The paper presents a review of the main statistical methods used to assess disease risk near a putative source of environmental pollution. Both techniques based on counts in area units (e.g. administrative units) and case-control studies are considered.