SPSS guide

Moderation vs mediation: what’s the difference?

Short answer

Moderation asks when or for whom an effect happens: a third variable changes the strength of the X → Y relationship. Mediation asks how or why it happens: X affects Y through a third variable. Moderation is tested with an interaction (PROCESS Model 1); mediation with an indirect effect (PROCESS Model 4).

Examples

  • Moderation: stress lowers wellbeing more for people with little social support. Support changes the strength of the effect.
  • Mediation: stress lowers wellbeing partly because it disrupts sleep. Sleep is the route the effect travels through.

How each is tested

Moderation: add the product X × W to a regression. A significant interaction means the effect of X depends on W; probe it with conditional effects at low, average and high W. Mediation: estimate a (X → M) and b (M → Y), multiply them, and test the indirect effect with a bootstrap confidence interval that shouldn’t include zero.

Quick test

If you can say “the effect is stronger when…”, it’s moderation. If you can say “the effect happens because…”, it’s mediation.

Step-by-step tutorials

Still not sure which test fits?

Answer a few questions and the free tool tells you the test, the SPSS menu path and an APA example.

More SPSS questions

All SPSS tutorials →