Chapter 2 Multiple Regression

Exercise 1:
The business problem facing a consumer products company is to measure the effectiveness of
different types of advertising media in the promotion of its products. Specifically, the company
is interested in the effectiveness of radio advertising and newspaper advertising (including the
cost of discount coupons). During a one-month test period, data were collected from a sample
of 22 cities with approximately equal populations. Each city is allocated a specific expenditure
level for radio advertising and for newspaper advertising. The sales of the product (in thousands
of dollars) and also the levels of media expenditure (in thousands of dollars) during the test
month are recorded, with the following results shown below.

City Sales ($ Radio Newspaper

Thousands) Advertising Advertising
($ ($
Thousands) Thousands)

1 973 0 40
2 1,119 0 40
3 875 25 25
4 625 25 25
5 910 30 30
6 971 30 30
7 931 35 35
8 1,177 35 35
9 882 40 25
10 982 40 25
11 1,628 45 45
12 1,577 45 45
13 1,044 50 0
14 914 50 0
15 1,329 55 25
16 1,33 55 25
17 1,405 60 30
18 1,436 60 30
19 1,521 65 35
20 1,741 65 35

Page 1|6
 21 1,866 70 40
22 1,717 70 40

a. State the multiple regression equation.

b. Interpret the meaning of the slopes, b1 and b2 in this problem.
c. Interpret the meaning of the regression coefficient b0,
d. Which type of advertising is more effective? Explain.

Exercise 2:
In Exercise 1 you used radio advertising and newspaper advertising to predict sales.
a. Perform a residual analysis on your results.
b. If appropriate, perform the Durbin-Watson test, using α = 0.05.
c. Are the regression assumptions valid for these data?

Exercise 3 :
In Exercise 1, you used radio advertising and newspaper advertising to predict sales .Use the
results from that problem.
a. Construct a 95% confidence interval estimate of the population slope between sales
and radio advertising.
b. At the 0.05 level of significance, determine whether each independent variable makes
a significant contribution to the regression model. On the basis of these results, indicate
the independent variables to include in this model.

Exercise 4
In Ex1, you used radio advertising and newspaper advertising to predict sales.Use the results
from that problem.
a. At the 0.05 level of significance, determine whether each independent variable makes
a significant contribution to the regression model. On the basis of these results, indicate
the most appropriate regression model for this set of data.

Page 2|6
 2 2
b. Compute the coefficients of partial determination, 𝑟𝑌21 and 𝑟𝑌12 and interpret their
meaning.,

Exercise 5:
A real estate association in a suburban community would like to study the relationship between
the size of a single-family house (as measured by the number of rooms) and the selling price of
the house (in thousands of dollars). Two different neighborhoods are included in the study, one
on the east side of the community(=0) and the other on the west side(=1) A random sample of
20 houses was selected, with the results stored in . For (a) through (k), do not include an
interaction term.

a. State the multiple regression equation that predicts the selling price, based on the
number of rooms and the neighborhood.
b. Interpret the regression coefficients in (a).
c. Predict the selling price for a house with nine rooms that is located in an east-side
neighborhood. Construct a 95% confidence interval estimate and a 95% prediction
interval.
d. Perform a residual analysis on the results and determine whether the regression
assumptions are valid.
e. Is there a significant relationship between selling price and the two independent
variables (rooms and neighborhood) at the 0.05 level of significance?

f. At the 0.05 level of significance, determine whether each independent variable makes
a contribution to the regression model. Indicate the most appropriate regression model
for this set of data.
g. Construct and interpret a 95% confidence interval estimate of the population slope
for the relationship between selling price and number of rooms.
h. Construct and interpret a 95% confidence interval estimate of the population slope
for the relationship between selling price and neighborhood.
i. Compute and interpret the adjusted 𝑟. 2
j. Compute the coefficients of partial determination and interpret their meaning.
k. What assumption do you need to make about the slope of selling price with number
of rooms? l. Add an interaction term to the model and, at the 0.05 level of significance,
determine whether it makes a significant contribution to the model.
m. On the basis of the results of (f) and (l), which model is most appropriate? Explain.

Page 3|6
 PRICE ROOMS NEIGHBORHOOD
305.7 6 0
307.5 8 0
340.2 9 0
346.5 12 0
308.2 8 0
338.8 9 0
334.1 11 0
312.2 8 0
327.8 9 0
335.4 9 0
319.4 7 1
383.8 13 1
339.9 10 1
348.7 10 1
346.1 9 1
327.2 8 1
332.9 8 1
345.8 9 1
363.3 11 1
351.9 9 1

Exercise 6:
In Ex 1, you used radio advertising and newspaper advertising to predict sales. Develop a
regression model to predict sales that includes radio advertising, newspaper advertising, and
the interaction of radio advertising and newspaper advertising.
a. At the 0.05 level of significance, is there evidence that the interaction term makes a
significant contribution to the model?
b. Which regression model is more appropriate, the one used in this problem or the one
used in Problem 14.6? Explain

Exercise 7:
The director of graduate studies at a college of business wants to predict the success of students
in an MBA program using two independent variables, undergraduate grade point average
(GPA) and GMAT score. A random sample of 30 students (stored in ) indicates that 20
successfully completed the program (coded as 1) and 10 did not (coded as 0).

Page 4|6
Success in MBA Undergraduate GMAT Success in MBA Undergraduate GMAT
Program GPA Score Program GPA Score

0 2.93 617 1 3.17 639

0 3.05 557 1 3.24 632

0 3.11 599 1 3.41 639

0 3.24 616 1 3.37 619

0 3.36 594 1 3.46 665

0 3.41 567 1 3.57 694

0 3.45 542 1 3.62 641

0 3.60 551 1 3.66 594

0 3.64 573 1 3.69 678

0 3.57 536 1 3.70 624

1 2.75 688 1 3.78 654

1 2.81 647 1 3.84 718

1 3.03 652 1 3.77 692

1 3.10 608 1 3.79 632

1 3.06 680 1 3.97 784

a. Develop a logistic regression model to predict the probability of successful

completion of the MBA program based on undergraduate grade point average and
GMAT score.
b. Explain the meaning of the regression coefficients for the model in (a).
c. Predict the probability of successful completion of the program for a student with an
undergraduate grade point average of 3.25 and a GMAT score of 600.
d. At the 0.05 level of significance, is there evidence that a logistic regression model
that uses undergraduate grade
point average and GMAT score to predict probability of success in the MBA program
is a good-fitting model?
e. At the 0.05 level of significance, is there evidence that undergraduate grade point
average and GMAT score each make a significant contribution to the logistic regression
model?
f. Develop a logistic regression model that includes only undergraduate grade point
average to predict probability of success in the MBA program.

Page 5|6
g. Develop a logistic regression model that includes only GMAT score to predict
probability of success in the MBA program.
h. Compare the models in (a), (f), and (g). Evaluate the differences among the models.

Page 6|6