Lecture 6

Question 1

Moderation

Answer 1

The relationship between xand y depends on a third variable z

Question 2

Multiplicative interaction model

Answer 2

Predictor, moderator and predictor x moderator –> outcome

Question 3

When to use a moderator?

Answer 3

When the hypothesis is conditional on a third variable z

Question 4

When is the hypothesis conditional?

Answer 4

• A relationship between 2 or more variables is dependent on the value of one or more variables
• An increase in x is associated with an increase in y, when condition z is met, but not when condition z is absent
• X has a positive effect on y, that gets stronger when z increases

Question 5

Marginal effect of x on y without interaction

Answer 5

coefficient = difference in y / difference in x

Question 6

Marginal effect of x on y with interaction

Answer 6

difference in y/ difference in x = coefficient of x + coefficient of z

The marginal effect of x is now a function of z. The effect of a change in x depends on the value of z.

Question 7

Mediation

Answer 7

The impact of x on y is driven by the presence of another variable w.

The relation (partly) runs via a third variable. Y depends on the mediator and the mediator depends on X.

Question 8

Quadratic term

Answer 8

When the IV doesnt give a linear relationship on the DV

This is included in the model by adding the square of the concerning IV.