Analysis of Covariance

Question 1

When and why would you use this?

Answer 1

To test for differences between group means when we know that an extraneous variable affects the outcome variable

used to adjust the means for extraneous and confounding variables

Question 2

What are you deliberately doing in this?

Answer 2

Adjusting means for things which you think may affect them

Question 3

What are the advantages of ANCOVA?

Answer 3

Can reduce error variance - by explaining some of the unexplained variance, the error variance in the model can be reduced

Greater experimental control - by adjusting for known confounds, we can gain greater insight into the effect of the predictor variable

Question 4

How do you partition variance?

Answer 4

The SSM and SSR is split into variance explained by the predictor and the covariate

Question 5

What happens to the means when you add a covariate?

Answer 5

They get adjusted - changes the mean

Question 6

What does homogeneity of regression slopes mean?

Answer 6

Covariate is consistent across 2 groups - manipulation needs to affect each group the same at each level

Question 7

Do we want the interaction to be significant?

Answer 7

No, if it significant, the assumption is broken

not significant = assumption met

Question 8

What is the additional assumption?

Answer 8

Homogeneity of regression slopes