Week 1 - Intro

Question 1

Define a factorial design (x2)

Answer 1

An analysis of variance/experiment with at least two factors (IVs),
Each with at least two levels

Question 2

What are three advantages of factorial designs?

Answer 2

Fewer PS than two one-way designs for same power, because we average over levels of the other factor
Allows us to examine the interaction of IVs
Generalisability of results can be assessed - ie, if not different across levels of the other factor

Question 3

List the types of research questions that can be addressed in a two-way (A x B) factorial design (x3)

Answer 3

Are means of populations corresponding to levels of first factor different - is there main effect of factor 1?
Are means of populations corresponding to levels of second factor different - is there main effect of factor 2?
Does the effect of one factor on DV scores depend on the level of the other factor - is there a factor 1 X factor 2 interaction?

Question 4

Indicate the general and specific notations for a factorial design with Factor A (e.g., with 2 groups/levels) and Factor B (e.g., with 3 groups/levels)

Answer 4

General - in words, by the number of factors involved, ie ‘two-way between-Ps factorial design
Specific - by the number of levels of each factor, ie 2 x 3 between-Ps factorial design

Question 5

Define marginal means (x2)

Answer 5

Mean of each factor, across all levels of the other

They’re in the margins of the paper

Question 6

What types of effects are marginal means used to test in a 2-way factorial ANOVA (x1)
How? (x2)

Answer 6

Main effects
If means are different to each other/grand mean, main effect is significant
If the same, then it’s not

Question 7

Define cell means (x1)

Answer 7

The mean of each combination of factors

Question 8

What types of effects are cell means used to test in a 2-way factorial ANOVA (x1)
How? (x2)

Answer 8

Simple effects - the effect of one factor at one level of the other
If cell means are different to each other, then significant simple effect
If same, then ns

Question 9

What is the difference between a main effect and simple effect (X2)

Answer 9

Main - the difference in marginal means (diffs in means across whole factor)
Simple - the difference between cell means (effect of one factor at one level, compared to same factor at other levels)

Question 10

Explain the difference between an ordinal interaction and a disordinal interaction (x2)

Answer 10

Ordinals - the lines don’t cross on graph

Disordinal - they do

Question 11

In a graph of a 2-way factorial ANOVA, explain how you would identify the main effects of the focal factor (x-axis)?
 (x3)

Answer 11

Look at the average across the second factor,
By ‘dotting’ half way between lines, and imagining vertical bars for each level
(Main effect if different heights)

Question 12

In a graph of a 2-way factorial ANOVA, explain how you would identify whether there is an interaction of the two factors?
 (x2)

Answer 12

If parallel lines, then there isn’t one

Otherwise there is (either ordinal or disordinal)

Question 13

In a graph of a 2-way factorial ANOVA, explain how you would identify the simple effects of each factor?

Answer 13

Line shows the simple effect of the focal IV (x-axis) at every level of the moderator (the line shows the moderating factor)

Question 14

What does it mean to say that interactions and main effects in a factorial design are independent? (x2)

Answer 14

That interactions and main effects can occur in any combination
ie you can have one or two main effects without interactions

Question 15

What does it mean to say that a significant interaction qualifies a significant main effect? (x1)

Answer 15

That simple effects of one IV depend on the level of the other IV

Question 16

In a graph of a 2-way factorial ANOVA, explain how you would identify the main effects of the line factor (factor b)?
 (x3)

Answer 16

Look at the average across the bar factor (on the x-axis)
By imagining crosses at the level of the average of both lines
(Significant if at different heights)

Question 17

What does it mean to ‘cross’ IVs in a design? (x2)

Answer 17

To examine them simultaneously, as in factorial

Rather than in separate one-way experiments

Question 18

Define ‘factor’ (x1)

Answer 18

An IV in an analysis of variance

Question 19

Define ‘level’ (x2)

Answer 19

One condition of one IV

Can be experimental or non (e.g. gender)

Question 20

Define ‘cell’ (x1)

Answer 20

A box in data table that shows the combination of one level of one factor with one level of another

Question 21

What is meant by ‘cell mean’? (x1)

Answer 21

The mean of scores on the DV at one level of one factor, and one level of another

Question 22

What do one-way designs/ANOVAs test? (x1)

What does a significant result mean? (x1)

Answer 22

Are the mean DV scores of populations for each level of the factor different from the grand mean (from each other)?
At least one level of the factor is different from the grand/other factors

Question 23

What is the grand mean? (x1)
What is it’s purpose in ANOVA? (x1)
Where is it displayed? (x1)

Answer 23

The mean of all observations
Not much, but is part of structural model
Bottom far right of data table

Question 24

Define interaction (x2)

Answer 24

The difference between simple effects (the effect of one factor at one level of the other factor)
When the effect of one factor is conditional upon/qualified/moderated by levels of the other

Question 25

What are the two classes of test in ANOVA?

Answer 25

Omnibus (everything) - all the variance in the IV; for main effects and interactions
Follow-ups - e.g. to see where main effects lie among the levels

Question 26

How can you see an interaction in a data table? (x2)

Answer 26

If the difference of the differences is zero, then there is no interaction
ie, the we have an interaction if the diffs in means of one factor (rows), across the levels of the other (columns), is not zero

Question 27

What is meant by ‘moderate/qualify’? (x1)

Answer 27

A moderating IV is one that changes the impact of a focal factor on the DV

Question 28

How do you lay out a factorial data table? (x2)

Answer 28

Factor A - the focal IV - goes on the left (rows)

Factor B - goes across the top (columns)

Question 29

How do you plot main effects and interactions? (x4)

Answer 29

y-axis - the DV
x-axis - factor with the most levels or factor which is most theoretically important
Other IV/line factor/moderator (fewer levels or less interesting) - represented by separate lines on the graph
All cell means (not marginal) must be represented

Question 30

How can a main effect be misleading? (x2)

Answer 30

If we don’t reinterpret them in light of interactions/moderation/qualification by the other IV,
We can miss that it may be strengthened/weakened based on levels of that other factor

Question 31

For each pair of factors in a factorial design, there are potentially… (x2)

Answer 31

Two main effects

One interaction

Question 32

What does a ‘main effect’ tell us? (x1)

Answer 32

That there is a difference in population means corresponding to a particular factor

Question 33

What does a ‘simple effect’ tell us?

Answer 33

That there is a difference between means in one particular factor, at different levels of another