Answer the following questions based on Section 3.4: Model assumptions.

1. 

True or false? Multiple linear regression relies on assumptions about the random errors in the model, which we assess using residuals.

2. 

Select the correct four assumptions about the probability distribution of the random errors at each set of predictor values in a multiple linear regression model.

3. 

Which multiple linear regression model assumption is contradicted by a residual scatterplot with residuals that form an approximate fan-shaped pattern?

4. 

Which multiple linear regression model assumption is contradicted by a residual scatterplot with residuals that display a curved trend?

5. 

Which multiple linear regression model assumption is contradicted by a residual QQ-plot (normal probability plot) with some points that lie far from the diagonal line?

6. 

Which multiple linear regression model assumption is contradicted by a residual scatterplot with time on the horizontal axis that shows adjacent residuals following each other closely?

7. 

Which multiple linear regression model assumption does the following method test? Apply an Anderson-Darling test to the residuals.

8. 

Which multiple linear regression model assumption does the following method test? Apply a Breusch-Godfrey test to the residuals.

9. 

Which multiple linear regression model assumption does the following method test? Apply a Breusch-Pagan or Cook-Weisberg test to the residuals.

10. 

Which multiple linear regression model assumption does the following method test? Apply a lack of fit test if there are replicates in the dataset.

11. 

Which multiple linear regression model assumption does the following method test? Fit a quadratic regression model of the residuals against a predictor in the model.

12. 

Which multiple linear regression model assumption does the following method test? Fit a simple linear regression model of the residuals against a predictor not in the model.

Categories:

Tags:

Comments are closed