Chapter 12:


Factorial Experiments


Outline

I. The 2 x 2 factorial design

A. Each column and each row of the 2 X 2 is like a simple experiment

B. How one experiment can do more than two

1. Four simple main effects

2. Two overall main effects

3. Interactions

4. Example of questions addressed by a 2 X 2 experiment

C. Why you want to look for interactions

D. Potential results of a 2 x 2 experiment

1. Main effect and no interaction

2. Two main effects and no interaction

3. Two main effects and an interaction

4. Interaction without main effects

5. One main effect and an interaction

6. No main effects and no interaction

II. Analyzing the results from a 2 x 2 experiment

A. What degrees of freedom tell you

B. What F and p values tell you

C. What main effects tell you

D. What interactions usually tell you

III. Putting the 2 x 2 to work

A. Adding a replication factor to increase

generalizability

B. Using an interaction to find an exception to the rule: Looking at a potential moderating factor

C. Using interactions to find new rules

D. Conclusions about putting the 2 X 2 Factorial Experiment to Work

III. Hybrid designs: Factorial designs that allow you to study non-experimental variables

      A. Hybrid design's key limitation: Can't make causal inferences about non-manipulated variable

      B. Reasons to use hybrid designs

1. To increase generalizability

2. To studying the effects of similarity

3. To find an exception to the rule

4. To increase power: The blocked design

IV. Concluding remarks

Summary

Key terms and Issues

Exercises


Back to Chapter 12 Main Menu