8. Comparing means adjusted for other predictors

Question 1

When do we compare means adjusting for other predictors using the linear model?

Answer 1

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

Question 2

What are the two reasons we compare means adjusting for other predictors using the linear model in experimental research?

Answer 2

1. Reduce error variance
2. Greater experimental control

Question 3

What is adjusting for other predictors using the linear model used for?

Answer 3

Used to adjust the means for extraneous and confounding variables

Question 4

The F-statistic is calculated using what?

Answer 4

Sums of squares

Question 5

Why does order of predictors matter in Type I sums of squares on R?

Answer 5

Because each predictor is evaluated taking account of previous predictors

Question 6

The order of predictors in Type III sums of squares on R doesn’t matter because…

Answer 6

Each predictor is evaluated taking account of all other predictors

Question 7

If you want F-statistics and have several predictors, what sums of squares should you use?

Answer 7

Type III sums of squares

Question 8

For the significance of F-statistics to be accurate, we assume what?
What is this known as?

Answer 8

That the relationship between the covariate and outcome is similar across groups
This is know as HOMOGENEITY OF REGRESSION SLOPES

Question 9

When we include both a categorical and continuous predictor, the categorical predictor compares…

Answer 9

means adjusted for the effect of the continuous predictor

Question 10

You can break down the effects of categorical predictors using what?

Answer 10

Parameter estimates and their associated tests