MANAGERIAL STATISTICS FINAL EXAM

Sample Questions

1. A record company executive is interested in estimating the difference in the average play
length of rock-and-roll singles and country-and-western singles. To do so she randomly
selects 10 country-and-western singles and nine rock-and-roll singles. The play lengths in
minutes of the selected singles are as follows:
Country and Western Rock and Roll
3.80 3.88
3.30 4.13
3.43 4.11
3.30 3.98
3.03 3.98
2.18 3.93
3.18 3.92
3.83 3.98
3.22 4.67
3.38
At a 0.01 level of significance, is there evidence to say that there is a significant
difference in the average playing length of time of the two populations? Use the 7-step
procedure. Then fill in the cells in the following Excel spreadsheet with their correct
figures.
t-Test: Two-Sample Assuming Equal Variances

Country and Western Rock and Roll

Mean * *
Variance * *
Observations * *
Pooled Variance *
Hypothesized Mean Difference *
df *
t Stat *
P(T<=t) one-tail 0.00010934
t Critical one-tail *
P(T<=t) two-tail 0.00021868
t Critical two-tail *
Answer. There is sufficient evidence to reject H0. The p-value is small and there is a
significant difference between the two population means.
t-Test: Two-Sample Assuming Equal Variances

Country &
Western Rock & Roll
Mean 3.265 4.064444444
Variance 0.210005556 0.058427778
Observations 10 9
Pooled Variance 0.138674837
Hypothesized Mean
Difference 0
df 17
t Stat -4.672334334
P(T<=t) one-tail 0.00010934
t Critical one-tail 2.566939656
P(T<=t) two-tail 0.00021868
t Critical two-tail 2.898232196

2. A producer of a certain brand of coffee claims that at least 20% of all coffee drinkers
prefer its product to the major competing brand. To test the validity of this claim, an
individual samples 200 coffee drinkers and finds that 43 prefer the producer’s brand. Test
the producer’s claim using a 0.05 level of significance. Follow the standard 8-step
procedure used in the lectures. Answer. The following PHSTAT output gives the
solution:
Z Test of Hypothesis for the Proportion

Data
Null Hypothesis p= 0.2
Level of Significance 0.05
Number of Successes 43
Sample Size 200

Intermediate Calculations
Sample Proportion 0.215
Standard Error 0.028284271
Z Test Statistic 0.530330086

Lower-Tail Test
Lower Critical Value -1.644853476
p-Value 0.702058477
Do not reject the null hypothesis

3. To what extent do syntax textbooks, which analyze the structure of sentences, illustrate
gender bias? A study of this question sampled sentences from ten texts. One part of the
study examined the use of the words “girl”, “boy”, “man”, and “woman”. We will call
the first two words juvenile and the last two words adult. Is the proportion of female
references that are juvenile (girl) equal to the proportion of male references that are
juvenile (boy)? Here are the data from one of the texts. Use α = 0.05.
 Gender n No. of juveniles
Female 60 48
Male 132 52
Answer. Let p1 = proportion of female references that are juvenile (girl) and let p2 =
proportion of male references that are juvenile (boy). According to the data,
48 52
pˆ1 = ˆ2 =
and p . This is a test concerning the difference of 2 proportions. The
60 132
following 7-step procedure applies: Rejection
H0: p1 - p2 = 0 vs. Rejection Region
Region
HA: p1 - p2 ≠ 0 This is a two-tailed test.
α = 0.05
α
pˆ1 − pˆ 2 = ..025 α
Test Statistic: z= 2 = .025
2
1 1
p (1 − p )( + ) Non Rejection Region
n1 n2
-Z0.025 = -1.96 Z0.025 = 1.96
Decision Rule: Reject H0 when z < -1.96 or z > 1.96 0
Computation: Critical Values

48 52
−
z= 60 132 = 5.22
100 92 1 1
( )( )( + )
192 192 60 132
Conclusion: There is sufficient evidence to reject H0. There is a significant difference
between the two proportions.

4. Researchers at the Oak Ridge (Tennessee) National Laboratory have developed a

computer program to estimate the numbers of expected cases of thyroid cancer occurring
in the lifetime of those exposed to atomic weapons test at the Nevada Test Site in the
1950s. Of the approximately 23,000 people exposed to the weapons testing fallout, 58
were expected to develop thyroid cancer in their remaining lifetimes. Suppose that the
data represent a random sample of 58 thyroid cancer patients selected from the target
population. Conduct a test to determine whether gender and dose at time of exposure are
independent. Use α = 0.01.
Male Female
Less than 1 6 13
1 - 10 8 18
At least 11 3 10
Answer. This is a test concerning independence of 2 variables of interest. The
following 7-step procedure applies:
H0: gender and dose at time of exposure are independent vs.
HA: gender and dose at time of exposure are related. This is a one-tailed test.
α = 0.01

Test Statistic: C=
rc
(oi − ei )2 df = 2
11
i =1 ei
Decision Rule: Reject H0 if C > 9.21 0.01
Computation: The expected Non Rejection
frequencies are obtained by region
(row total) × (column total)
grand total 24.725
9.21
and are summarized in the following table:
 Male Female Total
Less than 1 6 (5.569) 13 (13.431) 19
1 - 10 8 (7.621) 18(18.379) 26
At least 11 3 (3.810) 10 (9.190) 13
Total 17 41 58
(6 − 5.569) 2 (13 − 13.431) 2 (10 − 9.19) 2
C= + + ... + = 0.3174
5.569 13.431 9.19
Conclusion: We do not have sufficient evidence to reject H0. Gender and dose at time
of exposure are independent.

5. Food poisoning outbreaks are often the result of contaminated salads. In one study carried
out to assess the magnitude of that problem, the New York City Department of Health
examined 220 tuna salads marketed by various retail and wholesale outlets. A total of 179
were found to be unsatisfactory for health reasons. Find a 90% confidence interval for p,
the true proportion of contaminated tuna salads marketed in New York City. Answer. A
90% confidence interval for p is
179 (0.8136)(0.1864) 179 (0.8136)(0.1864)
( − (1.645) , + (1.645) )
220 220 220 220
0.77045 < p < 0.8568

6. A machine for filling cereal boxes can be set to dispense a mean weight of between 12
and 20 ounces. The standard deviation of the weight of boxes filled with the machine is 1
ounce and is independent of the mean µ. The product is shipped in cases of n = 36 boxes.
Assume each case represents a random sample from the population of boxes filled by this
machine at a fixed setting of the mean weight dispensed. What should the mean µ be so
that 95.05% of all cases produces will have a mean weight of more than 16 ounces?
Answer. µ = 16.275 ounces

7. A consumer test group wants to determine the difference in gasoline mileage of cars
using regular unleaded gas and cars using premium-unleaded gas. Researchers for the
group divided a fleet of 100 cars of the same make in half and tested each car on one tank
of gas. Fifty of the cars were filled with regular unleaded gas and 50 were filled with
premium-unleaded gas. The sample average for the regular gasoline group was 21.45
miles per gallon with a standard deviation of 3.46 miles per gallon. The sample average
for the premium gasoline group was 24.6 miles per gallon with the standard deviation of
2.99 miles per gallon. Construct a 95% confidence interval to estimate the difference in
the mean gas mileage between the cars using regular gasoline and the cars using premium
gasoline. Answer. A 95% confidence interval for µ1 - µ2 is
(3.46) 2 (2.99) 2
(21.45 − 24.6) − (1.96)( + < µ1 − µ 2 <
50 50
(3.46) 2 (2.99) 2
(21.45 − 24.6) + (1.96)( +
50 50
-4.4176 < µ1 - µ2 < -1.8824
8. Consider the following data on the number of hours that 10 persons study for a History
test and their scores on the test:
Hours studied (x) 4 9 10 14 4 7 12 22 1 17
Test Score (y) 31 58 65 73 37 44 60 91 21 84
10 10 10
(a) Determine the following sums: Yi = ____ Xi = ____ xiYi = _____
i =1 i =1 i =1

10 10
Yi 2 = _____, then use these sums to find the point estimates
2

i =1
x i
= _____
i =1
of β0 and β1 in the simple linear regression model Yi= β0 + β1xi + εi. Answer.
10 10 10 10
2

i =1
Yi = 564 ,
i =1
Xi = 100 ,
i =1
xiYi = 6945 ,
i =1
xi
= 1376 ,

(100)(564)
10 S xy 6945 −
10
Yi 2 = 36562 and b1 = = = 3.471 ;
i =1 S xx (100) 2
1376 −
10
10 10
Yi xi
b0 = i =1
− b1 i =1
= 21.693
10 10
(b) Predict the average test score of a person who studied 14 hours for the test. Answer.
µ Y x =14 = 21.693 + (3.471)(14) = 70.283
(c) Compute the correlation coefficient and the coefficient of determination and interpret
your results. Answer. r = 0.97625 and r2 = 0.9531
There is a strong positive linear relationship between X and Y. 95.31% of the total
variation in the Y values is accounted for or explained by the linear regression
model. This indicates that the linear model is an appropriate model for the data.

9. According to one study, “The majority of people who die from fire and smoke in
compartmented fire-resistive buildings – the type used for hotels, motels, apartments, and
other health care facilities – die in the attempt to evacuate”. The following data represent
the numbers of victims who attempted to evacuate for a sample of 14 fires at
compartmented fire-resistive buildings reported in the study.
Fire Died in Attempt to Evacuate
Las Vegas Hilton 5
Toronto Inn on the Park 5
Westchase Hilton, Houston 8
Holiday Inn, Ohio 10
Conrad Hilton, Chicago 4
Providence College 8
Atlanta Baptist Towers 7
Howard Johnson Inn, New Orleans 5
Cornell University 9
Westport Central Apartments 4
Orrington Hotel, Illinois 0
Hartford Hospital 16
 Milford Plaza, New York 0
MGM Grand, Las Vegas 36

State the assumption, in terms of the problem, that is required for a small-sample
confidence interval technique to be valid. Construct a 98% confidence interval for
the true mean number of victims per fire who die in an attempt to evacuate
compartmented fire-resistive buildings. Answer. We have to assume that the
number of people who die in an attempt to evacuate a compartmented fire-
resistive building is normally distributed. Since the variance is unknown and n
< 30, we can apply the t- distribution. Based on the data, the sample mean is
8.357143 and the sample standard deviation is 8.940893. A 98% confidence
interval for µ based on the data is
(8.357143 − (2.6503)(8.940893 ),8.357143 + (2.6503)(8.940893 ))
14 14
µ < 14.6895
2.0248 <µ

10. The response time in milliseconds was determined for three different types of circuits that
could be used in an automatic valve shut off mechanism. The results are shown in the
following table:
Circuit Type 1 Circuit Type 2 Circuit Type 3
9 20 6
12 21 5
10 23 8
8 17 16
15 30 7
(a) Test the hypothesis that the three circuit types have the same response time.
Show the ANOVA table and the standard 7-step procedure. Use α = 0.01. Answer. The
7-step procedure is
H0: µ1 = µ2 = µ3
HA: at least 2 means are not equal
α = 0.01
MSTR
Test Statistic: F=
MSE
Decision Rule: Reject H0 if F > F0.99, (2, 12) = 6.93
The following ANOVA table was generated by MINITAB

One-way ANOVA: ResponseTime versus CircuitType

Source DF SS MS F P
CircuitType 2 543.6 271.8 16.08 0.000
Error 12 202.8 16.9
Total 14 746.4

S = 4.111 R-Sq = 72.83% R-Sq(adj) = 68.30%

Individual 99% CIs For Mean Based on Pooled StDev

Level N Mean StDev ------+---------+---------+---------+---
1 5 10.800 2.775 (-------*-------)
2 5 22.200 4.868 (-------*-------)
3 5 8.400 4.393 (-------*-------)
------+---------+---------+---------+---
7.0 14.0 21.0 28.0
Pooled StDev = 4.111
 Conclusion: We have sufficient evidence to reject H0. There is a significant
difference among the mean response times for the three circuit types.
(b) Construct Tukey intervals to compare pairs of treatment means. Use α = 0.01.
Answer. The following Tukey intervals were generated by MINITAB
Tukey 99% Simultaneous Confidence Intervals
All Pairwise Comparisons among Levels of CircuitType

Individual confidence level = 99.62%

CircuitType = 1 subtracted from:

CircuitType Lower Center Upper ---------+---------+---------+---------+

2 2.116 11.400 20.684 (-------*------)
3 -11.684 -2.400 6.884 (-------*-------)
---------+---------+---------+---------+
-12 0 12 24

CircuitType = 2 subtracted from:

CircuitType Lower Center Upper ---------+---------+---------+---------+

3 -23.084 -13.800 -4.516 (------*-------)
---------+---------+---------+---------+
-12 0 12 24

From the Tukey intervals, we deduce that there is a significant difference between
the mean response times of Circuit Type 1 and Circuit Type 2. There is also a
significant difference between the mean response times of Circuit Type 2 and
Circuit Type 3. However, since zero is in the Tukey interval for Circuit Type 1 and
3, we cannot conclude that there is a significant difference in the mean response
times of these two circuit types.
 MULTIPLE CHOICE QUESTIONS

In the following multiple-choice questions, circle the correct answer.

1. The school's newspaper reported that the proportion of students majoring in business is at
least 30%. You plan on taking a sample to test the newspaper' s claim. The correct set of
hypotheses is
a. H0: p < 0.30 Ha: p ≥ 0.30
b. H0: p ≤ 0.30 Ha: p > 0.30
c. H0: p ≥ 0.30 Ha: p < 0.30
d. H0: p > 0.30 Ha: p ≤ 0.30

2. A regression analysis between demand (y in 1000 units) and price (x in dollars) resulted
in the following equation

Y = 9 – 3x

The above equation implies that if the price is increased by $1, the demand is expected to
a. increase by 6 units
b. decrease by 3 units
c. decrease by 6,000 units
d. decrease by 3,000 units

3. The numerical value of the coefficient of determination

a. is always larger than the coefficient of correlation
b. is always smaller than the coefficient of correlation
c. is negative if the coefficient of determination is negative
d. can be larger or smaller than the coefficient of correlation

4. The ANOVA procedure is a statistical approach for determining whether or not

a. the means of two samples are equal
b. the means of two or more samples are equal
c. the means of more than two samples are equal
d. the means of two or more populations are equal

5. The z value for a 97.8% confidence interval estimation is

a. 2.02
b. 1.96
c. 2.00
d. 2.29

6. If we change a 95% confidence interval estimate to a 99% confidence interval estimate,

we can expect the
a. width of the confidence interval to increase
b. width of the confidence interval to decrease
c. width of the confidence interval to remain the same
d. sample size to increase
7. To become an actuary, it is necessary to pass a series of 10 exams, including the most
important one, an exam in probability and statistics. An insurance company wants to
estimate the mean score on this exam for actuarial students who have enrolled in a special
study program. They take a sample of 8 actuarial students in this program and determine
that their scores are: 2, 5, 8, 8, 7, 6, 5, and 7. This sample will be used to calculate a 90%
confidence interval for the mean score for actuarial students in the special study program.

(a) True or False: Referring to Problem 7, for the confidence interval to be valid, it is
necessary that test scores of students in the special study program on the actuarial exam
be normally distributed.
(b) True or False: Referring to Problem 7, it is possible that the confidence interval
obtained will not contain the mean score for all actuarial students in the special class.
(c) True or False: Referring to Problem 7, if we use the same sample information to
obtain a 95% confidence interval, the resulting interval would be narrower than the one
obtained here with 90% confidence.

8. Microsoft Excel was used on a set of data involving the number of parasites found on 46
Monarch butterflies captured in Pismo Beach State Park. A biologist wants to know if the
mean number of parasites per butterfly is over 20. She will make her decision using a test
with a level of significance of 0.10. The following information was extracted from the
Microsoft Excel output for the sample of 46 Monarch butterflies:
n = 46; Arithmetic Mean = 28.00; Standard Deviation = 25.92; Standard Error = 3.82;
Null Hypothesis: H 0 : µ ≤ 20.000 ; α = 0.10; df = 45; T Test Statistic = 2.09;
One-Tailed Test Upper Critical Value = 1.3006; p-value = 0.021; Decision = Reject.

(a) True or False: Referring to Problem 8, the null hypothesis would be rejected if a
4% probability of committing a Type I error is allowed.
(b) True or False: Referring to Problem 8, the null hypothesis would be rejected if a
1% probability of committing a Type I error is allowed.
(c) True or False: Referring to Problem 8, the evidence proves beyond a doubt that
the mean number of parasites on butterflies in Pismo Beach State Park is over 20.
(d) True of False: Referring to Problem 8, the biologist can conclude that there is
sufficient evidence to show that the average number of parasites per butterfly is over 20
using a level of significance of 0.10.
(e) True or False: Referring to Problem 8, the biologist can conclude that there is
sufficient evidence to show that the average number of parasites per butterfly is over 20
with no more than a 1% probability of incorrectly rejecting the true null hypothesis.

Prepared by:
Mrs. Marian T. Reyes
For exclusive use of her students in the course
Managerial Statistics
De La Salle Professional Schools, Inc.
Graduate School of Business
RCBC Campus
No unauthorized use or reproduction