STAT 301 - Business Statistics
Lecture Review #27 - Evaluating Correlation and Regression Models

Review questions:

1) What is the covariance? What does it measure? How is it computed?

2) What is the correlation? How is it computed?

3) What does it mean if the correlation is positive? Negative? Zero? What is the largest (smallest) value a correlation can have?

4) What are the slope and intercept of a regression line? How are they computed?

5) As outlined in class, what three things should we check, to investigate the quality of a regression model?

6) What is the error variance of a regression model? How is it computed? Why do we divide by n-2 in finding the error variance?

7) What is the coefficient of determination? How is it interpreted? What other name does it have?

Computational exercises:

Anastasia Romanova collects data on the number of customers per day at a small retail store, and the store’s daily sales volume. Data are below:

a) Sketch an appropriate graph of the data. Does a linear fit appear reasonable?

b) Find the correlation coefficient for these data. Interpret this number.

c) Find the slope and intercept of the regression line for these data. Interpret these numbers.

d) Find the error variance for the model.

e) Give the coefficient of determination (r-square) for the model. Interpret this quantity.

SOLUTIONS:
b) corr = 0.8
c) slope = 20, intercept = 0
d) 157,500
e) 0.64