Coverage, is the extent to which the real, observed population matches the ideal or normative population. A population is the domain from which observations for a particular topic can be drawn.
Under-coverage results from the omission of units belonging to the target population, while over-coverage occurs due to the inclusion of elements that do not belong to the target population. For instance, for causes of death statistics, all deaths of residents occurring in a given year should be covered. However, information about residents dying abroad might not be included in all countries (resulting in under-coverage), and deaths of non-residents might be included (resulting in over-coverage).
An understanding of coverage is required to facilitate the comparison of data. Coverage issues are often explained through the use of tables showing linkages (e.g. part or full correspondence) and can also be used to explain the ratio of coverage. The rules and conventions of coverage are largely determined by concept definitions, scope rules, information requirements and, in the case of statistical collections and classifications, collection and counting units and the collection methodology.