Repeated measures ANOVA Flashcards

1
Q

How many IV levels are needed to have issues with sphericity?

A

3 or more

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Can Mauchley’s test of sphericity be used to assess compound symmetry?

A

Yes, but sphericity is a relaxed version of compound symmetry.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What does a significant Mauchley’s test reveal?

A

There is a significant violation of assumptions about sphericity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are the consequences for lacking homogeneity of variance in between groups ANOVA and lacking sphericity in within participants ANOVA?

A

Type 1 error bias, making it more likely to get significant results that are not real.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

When should we apply the Greenhouse-geisser epsilon adjustment?

A

Always apply the correction to be safe, as Mauchley’s test is not robust and often ignored all together.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Why is greenhouse-geisser epsilon adjustment most recommended?

A

The adjust it gives is proportional to the violation of sphericity observed.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What do higher epsilon values represent? Lower values?

A

Closer to 0 = larger adjustment to compensate (to be more conservative) greater sphericity violation
Closer to 1 = less adjustment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How do we overcome the fact that repeated measures designs violate the assumption of independent scores in ANOVA?

A

Participants are treated as a factor, which is cross with the focal IV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

In a within-participants ANOVA, what does between participants variance (aka individual differences) get removed from?

A

Both the error and the treatment effect

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What makes up the F test in WP ANOVA?

A

The treatment effect / (treatment x participants effect)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Why does the treatment x participants interaction serve as the error in WP ANOVA?

A

The interaction is the variance in the DV which is not attributable to any main effects alone. Because we want to remove the effect of participants (IV1), by design, and don’t want to consider the treatment variance again (IV2), the interaction (I.e. remaining variance) is an appropriate error term which excludes the effects of these two things.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

How do we frame error within a repeated measures ANOVA? What does this imply about the generality of error throughout the model?

A

Inconsistencies in the effect of the focal IV across participants. The error depends on the participants and treatment in focus; therefore cannot use pooled error terms for all tests.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is a fixed a factor?

A

Where either all levels of the IV have been sampled, or particular levels selected for theoretical reasons.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is a random factor?

A

A IV/factor where levels are chosen at random.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Two requirements for compound symmetry?

A
  1. Homogeneity of variance (diagonal matrix values)

2. Homogeneity of covariances

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

When do we require the assumption of compound symmetry to be met?

A

When using a random factor

17
Q

Which is the best multivariate test to use?

A

Wilks’ Lambda

18
Q

What are disadvantages of within-participants design? (2)

A
  1. Restrictive statistical assumptions

2. Confounds due to sequencing effects in the study

19
Q

Why is counterbalancing not a magical solution to order effects? (2)

A
  1. Carry-over effects still inflate error (although unsystematically due to random assignment to counter balance condition)
  2. There can still be treatment x order interactions
20
Q

What is the error term for every test in a RM ANOVA?

A

It is always the effect x participants interaction