One of the most commonly identified challenges in statistics for psychology is differentiating between *mediation* and *moderation*. Fully understanding these concepts can seem overwhelming, but it doesn’t have to be that way! All concepts that seem tricky can be broken down into simple, comprehendible steps.

**1.)** **What are ***independent* and *dependent* variables?

*independent*and

*dependent*variables?

In research, an *independent* variable, also known as a *predictor*, is the one being changed or controlled to test its effects on a *dependent* variable. A *dependent* variable, also known as an *outcome*, is the one that changes according to the independent variable.

For example, let’s say a researcher wants to assess how effective a new treatment for depression (treatment A) is in reducing patients’ depressive symptoms, relative to a control treatment (treatment B). To test this question, the researcher conducts a randomized controlled trial, randomizing patients to receive treatment A or treatment B and assessing patients’ symptoms of depression prior to and following treatment. In this example, the *independent* variable is treatment condition, and the *dependent* variable is change in patients’ symptoms of depression pre-treatment and post-treatment.

**2.)** **What is ***moderation*?

*moderation*?

*Moderation* occurs when a variable (i.e., a *moderator*) __influences__ the direction and / or strength of the relationship between the independent variable and the dependent variable.

Using the example in Step 1, it’s possible that a third variable might influence any identified relationship between treatment condition and symptoms of depression. For instance, it could be that participating in treatment A, on average, led to reductions in symptoms. However, it’s possible that this relationship is particularly strong for older patients, rather than younger patients. In this instance, the *moderator* is patient age because the relationship between the independent and dependent variables was __influenced__ by patient age.

Here’s another example. Research has shown that genetic vulnerability to depression predicts the development of depression. However, this relationship is influenced by life stress, with the link being strongest for people who experience life stress. In this instance, the *independent* variable is a genetic vulnerability to depression, the *dependent* variable is the development of depression, and the *moderator* is life stress.

**3.)** **What is ***mediation*?

*mediation*?

*Mediation* occurs when a variable (i.e., a *mediator*) __explains__ the relationship between the independent variable and the dependent variable.

Again, using the example in Step 1, it’s possible that a third variable might __explain__ the identified relationship between treatment condition and symptoms of depression. For instance, it could be that the effect of treatment A on depression symptoms is only present when patients completed their homework throughout therapy. In this instance, the *mediator* is whether or not the patients completed their therapy homework because the relationship between the independent and dependent variables was __explained__ by patient homework completion.

For more practice, let’s use our example focusing on the link between genetic vulnerability to depression and the development of depression. It’s possible that this relationship is not influenced but __explained__ by life stress, such that a genetic vulnerability *only* predicts the development of depression when life stress is experienced. In this instance, the *independent* variable is a genetic vulnerability to depression, the *dependent* variable is the development of depression, and the *mediator* is life stress.

Now you’re an expert on statistical *moderation* and *mediation*! To continue refining this skill, it’s helpful to practice identifying the independent, dependent, moderator and / or mediator variables in the academic articles that you might read in the future.

*Our statistics and probability tutors are doctoral candidates and PhDs. Our team also includes a small number of tutors, including MD and MBA candidates, who use statistics in the context of specialized fields. We help students master the fundamentals of statistics and probability: basic probability models, combinatorics (combinations and permutations), random variables, discrete and continuous probability distributions, statistical estimation and testing, confidence intervals, and linear regression. Whether you are encountering statistics for the first time, or you are looking for graduate level assistance in a specialized field, such as biostatistics or stochastic processes, we can help you.*

*Read more about statistics and probability below!*

## Why Understanding Statistics Matters More Than Ever

## Statistics Tutor: The 4 Keys to Conquering Statistics

## Data Science and Intuitive Mathematics