Attributable

Attributable is an adjective meaning capable of being attributed, ascribed, or credited to a particular cause, source, or agent. In everyday use, something is attributable to a factor if that factor is judged to be the reason or origin of it. The term is common in science, public discourse, and law to express causality or responsibility.

In epidemiology and related fields, attributable concepts quantify how much of a health outcome can be linked to a specific exposure. The attributable risk (AR) is the absolute difference in incidence between the exposed group and the unexposed group: AR = Ie − Iu, where Ie is the incidence in the exposed and Iu is the incidence in the unexposed. The attributable fraction among the exposed (AF or AFe) expresses this as a proportion of the risk in the exposed: AF = (Ie − Iu)/Ie = (RR − 1)/RR, with RR being the relative risk (RR = Ie/Iu). The population attributable fraction (PAF) estimates the proportion of all cases in the population that would be prevented if the exposure were eliminated, commonly written as PAF = [p(RR − 1)] / [p(RR − 1) + 1], where p is the prevalence of exposure.

Interpretation of attributable measures depends on a causal assumption: they describe potential impact under removing or reducing a factor, not just statistical associations. They can be affected by confounding, bias, and model choice, and do not alone prove causation.

Etymology: attributable derives from attribute (to assign) with the suffix -able, originating from Latin attribuere, meaning to assign or ascribe.