Week 10

Question 1

Do DV’s in MANOVA have to be conceptually related?

Answer 1

Yes.

Typically they are multiple ways to measure a concept.

Question 2

What is a benefit to using MANOVA?

Answer 2

Lower type 1 error rate than calculating several univariate ANOVA’s for each DV.

Question 3

For analysis via MANOVA, the DV’s:

Answer 3

1. Should be conceptually related

2. should be moderately correlated

Question 4

If you are planning to do a MANOVA but the DV’s are not correlated, what should you do instead?

Answer 4

Separate ANOVA’s with Bonferroni adjusted p values.

Question 5

If you are planning to do a MANOVA and the DV’s are too highly correlated:

Answer 5

There is a redundancy of information which loses power.

Question 6

What are two reasons that a MANOVA might lose power due to highly correlated DV’s?

Answer 6

1. multicollinearity

2. Singularity

Question 7

What is multicollinearity?

Answer 7

1. Very high correlations between variables

Question 8

What is singularity?

Answer 8

One variable is a combination of a number of others in the analysis.

Question 9

At minimum, in a MANOVA analysis, the number of DV’s should be:

Answer 9

Less than the number of cases.

Question 10

What are the assumptions for MANOVA?

Answer 10

1. independance of observations
2. multivariate normal distribution (large sample sizes help with this)
3. homogeneity of variance for all groups

Question 11

MANOVA has to be what type of subjects?

Answer 11

Between

Question 12

Homogeneity of variance in a MANOVA is usually okay if there are an equal number of participants in each cell. But, to be sure, what are two ways we can check this?

Answer 12

1. Levene’s test

2. Box’s test

Question 13

Describe Box’s test

Answer 13

very sensitive to violations of multivariate normality so pay little attention to it unless unequal sample sizes (or p

Question 14

If you have a significant Box’s test, what’s one thing you can do after this?

Answer 14

Do a Levene’s test to see where the problematic DV might be

Question 15

What is the default multivariate test of significance we should use in a MANOVA?

Answer 15

Wilks Lambda - generally recommended unless some possible assumption violations

Question 16

Which multivariate test of significance should we do for a MANOVA of the design is flawed (small n, unequal numbers etc) or is we have a significant Box’s test?

Answer 16

Pillai’s Trace.

Question 17

Wilks Lambda is equal to what in regard to variance?

Answer 17

Unexplained variance. So, variance accounted for by the best linear combination of DV’s (aka the MANOVA) = 1 - Wilks Lambda.

This is how we can work out the effect size for MANOVA.

Question 18

Pillai’s V is what in regard to effect size?

Answer 18

The proportion of variance accounted for by the best linear combination of DVs.

Question 19

What do we do if we have a significant MANOVA?

Answer 19

1. separate univariate tests of all DV’s. One ANOVA DV at a time.
2. step down analysis using ANCOVA.

Question 20

What happens if the MANOVA is not significant?

Answer 20

Differences here may be type 1 errors. Safest thing to do is report there was no significant differences and don’t do any further analysis.

Question 21

MANOVA _____ be more sensitive at detecting differences between IVs.

Answer 21

MAY

Question 22

What is preferable to have in data with MANOVA?

Answer 22

Preferable to have large samples, equal sample sizes and no outliers.