Interaction: modification of the association between an exposure and outcome on the variation of a third factor

Abstract

From a statistical perspective, interaction (effect modification) occurs when the effect of an exposure on an outcome depends on the level of another factor. In epidemiology, effect modification (interaction) occurs if the joint effect of two (or more) factors is different from the expected effect if considering only their independent effects. In an additive model, the effect of one exposure is added to effect of another exposure, and there is interaction if the joint effect of the two exposures together is greater than the sum of their individual effects. In a multiplicative model, the effect of the second exposure multiplies the effect of the first exposure, and there is interaction if the joint effect of the two exposures together is greater than the product of their individual effects. Interaction of two (or more) factors is synergic or antagonistic if the total effect is, respectively, greater or smaller than the sum of the individual effects of each factor. (Epidemiology_statistics)