4: Path Models and Mediation

Question 1

What is the implied correlation in a path model?

Answer 1

The sum of compound paths.

Question 2

What are direct effects?

Answer 2

A single, forward facing arrow.

Question 3

What are indirect effects?

Answer 3

A sequence of forward facing, single headed arrows through mediators.

Question 4

What is another name for indirect effects?

Answer 4

Composite pathways.

Question 5

What are spurious effects?

Answer 5

Sequences (with backward arrows) where variables share a common cause which makes them appear to be related.

Question 6

What are unanalysed effects?

Answer 6

Page involving a curved arrow that show a prior common cause represented outside the model.

Question 7

What is the total effect?

Answer 7

The combination of direct and all indirect pathways.

Question 8

What are under-identified models?

Answer 8

There are more parameters than observer information, so the model can not be uniquely estimated.

Question 9

What are just-identified models?

Answer 9

Numbers of observed information matches the number of parameters, so the model has a unique solution.

Question 10

What are over-identified models?

Answer 10

There are less parameters than observed relationships, so the model and the quality of the solution can be estimated.

Question 11

What are the 2 forms of error in path models?

Answer 11

The difference between a prediction and a score, and the difference between implied and actual correlation matrices.

Question 12

How are path models estimated?

Answer 12

By coming up with values for the path coefficients that minimise the difference between the implied and observer correlations.

Question 13

What is step 1 of classical mediation?

Answer 13

Establish that X -> Y and estimate c using regression.

Question 14

What is step 2 of classical mediation?

Answer 14

Establish that X -> M and estimate a using regression.

Question 15

What is step 3 of classical mediation?

Answer 15

Establish that the mediator impacts in the DV while controlling for the IV and estimate b while controlling for X.

Question 16

What is step 4 of classical mediation?

Answer 16

If c’ becomes 0 (or non sig.) then M completely mediates the relationship between X and Y.

Question 17

Why is step 1 of the classic model not always necessary?

Answer 17

Mediation can occur eve if the zero-order correlation between X and Y is small.

Question 18

What are 2 limits of the classic model?

Answer 18

Too little focus in trying to understand the implied model and it gets too complicated even there are more than 3 variables.

Question 19

How does the PROCESS approach estimate the parameters of a model?

Answer 19

Using a series of regressions.

Question 20

How does the PROCESS approach estimate the significance of indirect effects?

Answer 20

Using bootstrapping methods.

Question 21

What type of statistical errors can collinearity lead to?

Answer 21

Type I and II errors.

Question 22

Give 3 distortions collinearity can lead to.

Answer 22

Amplified parameters, larger standard errors, and far apart betas.

Question 23

When do suppression effects occur?

Answer 23

When the greater part of collinearity is irrelevant to the outcome/DV.

Question 24

What is suppression, in terms of shared irrelevant information?

Answer 24

The suppressor shares more with the other precursor than the DV.

Question 25

What happens in negative suppression?

Answer 25

One of the path weights reversed direction relative to the correlation.

Question 26

Define classic suppression.

Answer 26

The suppressor has 0 correlation with the DV but correlates with the IV, controlling irrelevant variance and increasing prediction.

Question 27

How do we most often see suppression?

Answer 27

As a special case of collinearity when trying to “control” highly correlated predictors.