University of Venda.

Module: MAT 2148 (Mathematical Modelling I).

Problem Sheet 2.
Date Issued: 19 March 2024

1 Reliability Modelling
1. Consider a stereo with CD player, FM-AM radio tuner, speakers (dual), and power
amplifier (PA) components, as displayed with the reliabilities shown in Figure be-
low. Determine the system’s reliability. What assumptions are required in your
model?

2. Consider a personal computer with each item’s reliability as shown in Figure be-
low. Determine the reliability of the computer system. What assumptions are
required?

1
3. Consider a more advanced stereo system with component reliabilities as dis-
played in Figure below. Determine the system’s reliability. What assumptions are
required?

4. Two alternative designs are submitted for a landing module to enable the trans-
port of astronauts to the surface of Mars. The mission is to land safely on Mars,
collect several hundred pounds of samples from the planet’s surface, and then
return to the shuttle in its orbit around Mars. The alternative designs are dis-
played together with their reliabilities in Figure below. Which design would you
recommend to NASA? What assumptions are required? Are the assumptions
reasonable?

2
2 Regression Modelling
1 The following data represent commute times (in minutes) and score on a well-
being survey

Commute Time(minutes), x Well-being Index Composite Score, y

5 69.2
15 68.3
25 67.5
35 67.1
50 66.4
72 66.1
105 63.9

1.1 Find the least-squares regression line treating the commute time, x, as the
explanatory variable and the index score, y, as the response variable.
1.2 Interpret the slope and y-intercept, if appropriate.
1.3 Predict the well-being index of a person whose commute is 30 minutes.
1.4 Suppose Mloche has a 20-minute commute and scores 67.3 on the survey.
Is Mloche more ”well-off” than the typical individual who has a 20-minute
commute?
1.5 Determine the coefficient of determination, and interpret it to comment on
the adequacy of the linear model.

2 Your credit score is used to determine your creditworthiness. It is used to help

determine whether you qualify for a mortgage or credit and is even used to de-
termine insurance rates. Credit scores have a range of 300 to 850, with a higher
score indicating a better credit history. The given data in the table represent the
interest rate (in percent) a bank would offer on a 36-month auto loan for various
credit scores.

Credit Score, x Interest rate(%), y

545 18.982
595 17.967
640 12.218
675 8.612
705 6.680
755 5.180

2.1 Find the least-squares regression line treating the credit score, x, as the
explanatory variable and the interest rate, y, as the response variable.
2.2 Interpret the slope and y-intercept, if appropriate noting that credit scores
have a range of 300 to 850.
2.3 Predict the interest rate a person would pay if his/her credit score were the
median score of 723.

3
 2.4 Suppose you have a credit score of 680 and you are offered an interest rate
of 8.3%. Is this a good offer? Why?
2.5 Determine the coefficient of determination, and interpret it to comment on
the adequacy of the linear model.

3 One of the biggest factors in determining the value of a home is the square
footage. The following data represent the square footage and selling price (in
thousands of dollars) for a random sample of homes for sale in Centurion, Gaut-
eng Province in January 2015.

Square footage, x Selling price(000), y

2204 379.9
3183 375
1128 189.9
1975 338
3101 619.9
2769 370
4113 627.7
2198 375
2609 425
1708 298.1
1736 271
3813 690.1

(a) Find the least-squares regression line treating square footage as the ex-
planatory variable.
(b) Interpret the slope.
(c) One home that is 1465 square feet is sold for R285,000. Is this home’s
price above or below average for a home of this size? What might be some
reasons for this price?
(d) Determine the coefficient of determination, and interpret it to comment on
the adequacy of the linear model.

4 After the first test (2018) in a Mathematical Modelling course (formerly MAT2548
and now MAT2148), the lecturer surveyed 14 randomly selected students to de-
termine the relationship between the amount of time they spent studying for the
test and test score. He found that a linear relationship exists between the two
variables. The least-squares regression line that describes this relationship is
y = 6.3333x + 53.0298.

4.1 Predict the exam score of a student who studied 2 hours

4.2 Interpret the slope
4.3 What is the mean score of students who did not study?
4.4 A student who studied for 5 hours for the exam scored 81 on the test. Is this
student’s test score above or below average among all students who studied
for 5 hours?

4
5 Is there a relation between the age difference between husband/wife and the
percentage of a country that is literate? Researchers found the least-squares
regression between age difference (husband age minus wife age), y, and literacy
rate (percent of the population that is literate), x, is y = −0.0527x+7.1. The model
is applied for 18 ≤ x ≤ 100.

5.1 Interpret the slope

5.2 Predict the age difference between husband/wife in a country where the
literacy rate is 25 percent.
5.3 Would it make sense to use this model to predict the age difference between
husband/wife in a country where the literacy rate is 10 percent? Explain
5.4 Suppose the literacy rate in South Africa is 79 percent and the age difference
between husbands and wives is 2 years. Is this age difference above or
below the average age difference among all countries whose literacy rate is
99 percent?