Abstract
The definitions of a biologic interaction and causal interdependence are reconsidered in light of a sufficient-component cause framework. Various conditions and statistical tests are derived for the presence of biologic interactions. The conditions derived are sufficient but not necessary for the presence of a biologic interaction. Through a series of examples it is made evident that in the context of monotonic effects, but not in general, the conditions which are derived are closely related but not identical to effect modification on the risk difference scale.
Disciplines
Epidemiology
Suggested Citation
VanderWeele, Tyler J. and Robins, James, "Biologic Interaction and Their Identification" (September 2006). COBRA Preprint Series. Working Paper 12.
https://biostats.bepress.com/cobra/art12