Week Ten - MANOVA Flashcards

1
Q

What is a MANOVA?

A

When we have more than one DV (can be on different scales)

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

what does a MANOVA promote?

A

Lower type I error

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

When should we use a MANOVA?

A

If the goal of the design is to discover whether behaviour, as reflected by the DVs, is changed by manipulation of the IV

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

What does MANOVA test for and what does this result in?

A

Differences on a linear combination of the DVs.

Results in potentially being more powerful/sensitive in identifying differences between groups - because it is examining differences along a combination of variables rather than just examining differences on a single variable

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

For MANOVA, the DVs must be? (2)

A

Conceptually related (theoretical reasons)

Moderately correlated (use ANOVA if not) - cannot be too highly correlated either (results in redundancy of power)

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

Too highly correlated DVs may be due to what? (2)

A

Multicollinearity: Very high correlations between variables

Singularity: One variable is a combination of a number of others in the analysis

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

A correlation score of .85 or above means what?

A

That the DVs are just measuring the same thing and we should just look at one or the other based on the theory

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

What are the assumptions of MANOVA?

A

INDEPENDENCE OF OBSERVATIONS: random allocation

MULTIVARIATE NORMAL DISTRIBUTION

HOMO OF VARIANCE (OF THE VARIANCE-COVARIANCE MATRICES)

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

What is HOV(VC) in MANOVA?

A

We need HOV for each group AND the correlation between DVs needs to be the same in each group (assumes that the data in each cell comes from a single population)

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

How do we check for HOV(CV)?

A

Levenes’s test

Box’s test: sig means violated

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

When should we pay attention to Box’s test?

A

When we have unequal sample sizes as it is very sensitive to violations of multivariate normality

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

MANOVA is reasonably robust to violations of HOV(CV) if?

A

There are equal numbers of participants per cell

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

What multivariate test of significance does MANOVA produce?

A

Wilks Lambda

Pillai’s Trace

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

When do we use Wilks Lambda?

A

Always unless there are some possible assumption violations

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

When do we use Pillai’s Trace?

A

When the design is flawed/violated - eg small sample size, unequal numbers

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

What do you do if MANOVA is significant?

A

Do separate univariate tests of all DVs (if correlations between dvs are low) so like normal anova with post-hoc follow up

17
Q

What do you do if MANOVA is not significant?

A

Nothing - could use effect size to build argument