In statistics, the **principle of marginality** refers to the fact that the average (or main) effects, of variables in an analysis are *marginal* to their interaction effect. The principle of marginality argues that, in general, it is wrong to test, estimate, or interpret main effects of explanatory variables where the variables interact or, similarly, to model interaction effects but delete main effects that are marginal to them. While such models are interpretable, they lack applicability, as they ignore the effects of their marginal main effects.

Nelder and Venables have argued strongly for the importance of this principle in regression analysis.