What is the difference between moderation and mediation?
Moderation and mediation are two very different ideas, so it is a little unfortunate that they not only have such similar names, but also tend to accompany the same citation: Baron and Kenny (1986). We’ll focus on the differences between moderation and mediation, though there are some important similarities.
Both analyses help us understand the relationship between an independent and dependent variable. Both mediation and moderation examine how a third variable impacts the relationship between an independent and dependent variable. For the purposes of understanding these two concepts, this is where the similarities end.
Moderation checks if a third variable influences the strength or direction of the relationship between the independent and dependent variables. A moderator variable can change the strength of a relationship, making it strong, moderate, or even non-existent. The moderator acts like a dial on the relationship. It adjusts its values can cause a previously observed statistical relationship to disappear. For example, if you expected that study time relates to grades on a calculus test, you would likely be correct.
Let’s say time spent studying strongly relates to grades. However, that relationship may not hold true across the board; something like grade level might be a possible moderator. If you change the moderator from college student to elementary school student, that relationship is unlikely to hold. Studying won’t help a second grader ace calculus, but it will significantly impact a college student’s score.
Mediation is a little more straightforward in its naming convention. A mediator mediates the relationship between the independent and dependent variables – explaining the reason for such a relationship to exist. Another way to think about a mediator variable is that it carries an effect. In a perfect mediation, an independent variable leads to some kind of change to the mediator variable, which then leads to a change in the dependent variable. However, in practice, researchers test the relationships between the independent variable, mediator, and dependent variable for correlation, not causality.
The purpose of mediation analysis is to see if the influence of the mediator is stronger than the direct influence of the independent variable. An obvious real-life mediator is temperature on a stove. Water will not start to boil until you have turned on your stove, but it is not the stove knob that causes the water to boil, it is the heat that results from turning that knob. To test this, we could check how strongly the knob turning correlates with the water’s state (i.e., whether it’s boiling).
For the first few minutes there would be no effect, so we can treat that as a weak correlation. Compared to the relationship between the temperature of your stove top and the state of the water, we can see that it is actually the temperature of the stove (the mediator) that is causing the water to boil, not just the action of turning a knob (the independent variable). Comparing the strength of these effects gives you insight into what is really carrying the effect on the water (the dependent variable).