1

NAME………………………………………………..
STUDENT NUMBER…………..……………………

UNIVERSITY OF NEW ENGLAND

UNIT NAME: QM 161

PAPER TITLE: BUSINESS STATISTICS

PAPER NUMBER: FIRST AND ONLY

DATE: (for examinations to enter) TIME: (for examinations to enter)

TIME ALLOWED: Two (2) hours plus fifteen minutes reading time

NUMBER OF PAGES IN PAPER: NINETEEN (19)

NUMBER OF QUESTIONS ON PAPER: FOUR (4)

NUMBER OF QUESTIONS TO BE ANSWERED:

STATIONERY PER CANDIDATE: 0 6 LEAF A4 BOOKS 1 ROUGH WORK BOOK

12 LEAF A4 BOOKS 0 GRAPH PAPER SHEETS

OTHER AIDS REQUIRED: FORMULA SHEET AND STATISTICAL TABLES

INCLUDED ON PAGES 15-19

POCKET CALCULATORS PERMITTED: YES

TEXTBOOKS OR NOTES PERMITTED: NIL

INSTRUCTIONS FOR CANDIDATES:

 Candidates MAY NOT make notes on this examination question paper during the fifteen
minutes reading time.
 Answer all questions
 Answers are to be written in the spaces provided on the examination question paper
 If you require more space for your answers, please write on the back of the page
 A Formula Sheet and Statistical Tables are provided on pages 15-19
 Examination question paper MUST BE HANDED in with the rough work book

REMEMBER TO WRITE YOUR NAME AND STUDENT NUMBER AT THE TOP OF THIS PAGE

THE UNIVERSITY CONSIDERS IMPROPER CONDUCT IN EXAMINATIONS TO BE A SERIOUS OFFENCE.

PENALTIES FOR CHEATING ARE EXCLUSION FROM THE UNIVERSITY FOR ONE YEAR AND/OR CANCELLATION
OF ANY CREDIT RECEIVED IN THE EXAMINATION FOR THAT UNIT.
 Question 1 (5 + 10 + 10 = 25 Marks)

Part A (Please circle your answer)

(1) The method involving the collection, presentation, and characterization of a set of
data in order to properly describe the various features of that set of data is called
(a) scientific method
(b) statistical inference
(c) descriptive statistics
(d) none of the above

(2) The universe or "totality of items or things" under consideration is called

(a) a sample
(b) a statistic
(c) a population
(d) a parameter.

(3) The portion of the universe that has been selected for analysis is called
(a) a sample
(b) a statistic
(c) a population
(d) a parameter.

(4) A summary measure that is computed to describe a characteristic of an entire

population is called
(a) a census
(b) a statistic
(c) a parameter
(d) the scientific method.

(5) A summary measure that is computed to describe a characteristic from only a

sample of the population is called
(a) a census
(b) a statistic
(c) the scientific method
(d) a parameter.

Question 1 is continued on next page

2
Part B

A new independent electricity provider in Country ABC has implemented a house-to-house

campaign to encourage customers to shift to their company. On one day of door knocking
seven staff reported the following number of households that were persuaded to switch to
Country ABC.

7 5 8 2 8 10 6

(a) Calculate the mean number of electricity provider changes per staff member
employed per day.

X
X 
46
 6.57(2 dec. places )
n 7

(b) Median: 7 Mode: 8

(c) Calculate the standard deviation.

1  2 ( X ) 2 
S   X  
n 1  n 

1  (46) 2 
S  342    6.619  2.57 (2 dec. places)
7 1  7 

(d) What does the Z-score measure? Using the information in (a) and (c), compute
the Z-score of 9.

Z score is a measure of relative position in standard deviation units.

X  X 9  6.57
Z =  0.95(2 dec. places)
S 2.57

Question 1 is continued on next page

3
Part C
Identifying managers who are both talented and motivated is difficult. A human resources
manager assessed 110 (112) staff and constructed a table with nine combinations of talent and
motivation levels.

Talent
Motivation Level High Medium Low Total
High 6 18 6 30
Medium 21 35 6 62
Low 12 6 2 20
Total 39 59 14 112

(a) A managerial prospect with “high motivation” is an example of a simple event.

True or False (please circle).

(b) A managerial prospect with “high motivation” and “high talent” is an example
of a joint event. True or False (please circle)

(c) Suppose the human resource manager has decided to hire a new manager, what
is the probability that the new manager
i. is in the high motivation category?

P(high motivation category) = 30/112 = 0.2679

ii. is in the high talent category?

P(high talent category) = 39/112 = 0.3482

iii. is high in both categories?

P(high in both categories) = 6/112 = 0.0536

iv. is medium in motivation given a manager high in talent has been

selected?

P(medium motivation | high talent) = 21/39 = 0.5385

(d) Are high motivation and high talent independent? Justify your answer.

P(High motivation) = 0.2679

P(High talent) = 0.3482
P(High both) = 0.0536
To be independent:
P(High both) = P(high motivation) X P(high talent)
0.0536  0.0933
High motivation and high talent are not independent

4
 Question 2 (5 + 10 +10 = 25 Marks)

Part A (Please circle your answer)

(1). The collection of all possible events is called

(a) a joint probability.
(b) a sample space.
(c) the null set.
(d) a simple probability.

(2). All the events in the sample space that are not part of the specified event are called
(a) the sample space.
(b) the complement of the event.
(c) joint events.
(d) simple events.

(3). A probability distribution

(a) associates a particular probability of occurrence with each
outcome in the sample space.
(b) assigns a value to the variability in the sample space.
(c) assigns a value to the centre of the sample space.
(d) None of the above.

(4). In a binomial distribution

(a) the results of one trial are dependent on the results of the other trials.
(b) the random variable X is continuous.
(c) the number of trials n must be at least 30.
(d) the probability of success p is stable from trial to trial.

(5). If two equally likely events A and B are mutually exclusive and collectively
exhaustive, what is the probability that event A occurs?
(a) 0
(b) 0.50
(c) 1.00
(d) Cannot be determined from the information given.

Question 2 is continued on next page

5
Part B

Adrian sells cars for Honest Joe’s car dealership. Adrian has never sold more than three cars
in a given week. Given X is the number of cars sold by Adrian in a week, the probability
distribution of X is summarized in the following table:

X 0 1 2 3
P(X) 0.25 0.45 0.25 0.05

(a) What is the probability of Adrian selling zero cars?

P(X=0) = 0.25

(b) What is the probability of Adrian selling at least two cars?

P(X2) = 0.25 +0.05 = 0.30

(c) What is the probability of Adrian selling no more than one car?

P(X1) = 0.25 +0.45 = 0.70

(d) Draw the probability distribution in a graphical form.

0.5

0.45

0.4

0.35

0.3
P(X)

0.25

0.2

0.15

0.1

0.05

0
0 1 2 3
X

(e) Adrian gets paid a bonus of $500 if he sells one car per week. For each
additional car sold per week Adrian receives $300. Calculate his mean bonus.

No. of cars Probability Bonus ($)

sold
0 0.25 0 0
1 0.45 500 225
2 0.25 800 200
3 0.05 1100 55
Mean bonus $480
Question 2 is continued on next page
6
Part C
Based on the records of Department of Immigration and Citizenship, the percentage of
applicants from the humanitarian stream program who failed the citizenship test is 16%.
Consider 20 applicants for Australian citizenship. Relevant PHStat output is provided on the
next page.

(a) What is the expected number of applicants who fail? Interpret this value.

E(X) =  = np = 20*0.16 = 3.2

The expected number of applicants from the humanitarian stream who

would fail the citizenship test is 3.2.

{If we repeat the experiment of sampling 20 applicants from the humanitarian scheme, the
average number of applicants who will fail the test will tend towards the true population mean
of 3.2}

(b) What is the probability that exactly 3 applicants will fail the test?

P(X=3) = 0.241

(c) What is the probability that fewer than 2 applicants will fail the test?

P(X<2) = 0.1471

(d) What is the probability that exactly 16 applicants will pass the test?

P(X’=16) = P(X=4) = 0.1951

(e) What are the characteristics of this binomial distribution?

o Two outcomes, success (item of interest) and failure (not item of

interest)
o Fixed number of trials, n = 20.
o Probability of success is constant between trials
o Independence from trial to trial

Question 2 is continued on next page

7
Binomial Probabilities

Data
Sample size 20
Probability of success 0.16

X P(X) P(<=X) P(<X) P(>X) P(>=X)

0 0.03059 0.03059 0 0.96941 1
1 0.116535 0.147125 0.03059 0.852875 0.96941
2 0.210873 0.357998 0.147125 0.642002 0.852875
3 0.240998 0.598996 0.357998 0.401004 0.642002
4 0.195093 0.794089 0.598996 0.205911 0.401004
5 0.118914 0.913003 0.794089 0.086997 0.205911
6 0.056626 0.969629 0.913003 0.030371 0.086997
7 0.021572 0.991201 0.969629 0.008799 0.030371
8 0.006677 0.997878 0.991201 0.002122 0.008799
9 0.001696 0.999573 0.997878 0.000427 0.002122
10 0.000355 0.999929 0.999573 7.14E-05 0.000427
11 6.15E-05 0.99999 0.999929 9.93E-06 7.14E-05
12 8.79E-06 0.999999 0.99999 1.14E-06 9.93E-06
13 1.03E-06 1 0.999999 1.06E-07 1.14E-06
14 9.81E-08 1 1 7.94E-09 1.06E-07
15 7.48E-09 1 1 4.66E-10 7.94E-09
16 4.45E-10 1 1 2.06E-11 4.66E-10
17 1.99E-11 1 1 6.47E-13 2.06E-11
18 6.33E-13 1 1 1.41E-14 6.47E-13
19 1.27E-14 1 1 0 1.41E-14
20 1.21E-16 1 1 0 0

8
 Question 3 (10 + 10 + 5 = 25 marks)

Part A

Time spent using email per session is normally distributed with a mean of 20 minutes and a
standard deviation of 3 minutes.
(a) What is the probability that time spent using email per session is greater than 21
minutes?

P(X > 21) = P (Z> 0.33) = 1-P(Z<0.33) = 1-0.6293 = 0.3707

(b) What is the probability that time spent using email per session is between 18.3
minutes and 22.6 minutes?

P(18.3 < X < 22.6) = P(-0.57 < Z < 0.87) = P(Z<0.87) – P(Z<-0.57)
= 0.8078 – 0.2843 = 0.5235

(c) What is the probability that a random sample of 64 email users will spend an
average time greater than 21 minutes?
As X ~ N, then the sampling distribution is also normal
P( X >21) = P(Z> 2.67) = 1-P(Z<2.67) = 1 – 0.9962 = 0.0038

(d) Explain the difference between the results in part (a) and part (c).

(A) Distribution of the parent population (X)

(C) Distribution of a sample statistic (sample mean) –sampling
distribution

Question 3 is continued on next page

9
Part B

The owner of a Greek restaurant wants to know the mean amount spent per customer in the
restaurant. A sample of 60 customers is taken. The sample mean is $38.54 and the standard
deviation is $7.26.

(a) Construct a 95% confidence interval for the mean amount spent per customer.
Give the confidence interval limits correct to two decimal places.
 7.262 
 is unknown but the sample size is large so by CLT we have X ~ N   , .
 60 
Our 95% confidence interval for  is given by:
X  Z 2  S  n 
Given the sample data, we have:

38.54  1.96  7.26 / 60 
38.54  1.84
($36.70, $40.38)

(b) Given the customer base remains the same the owner’s accountant has stated that
the mean amount spent per customer needs to be $45.00 in order to ensure that the
business remains profitable. Should the owner be concerned about the profitability
of the restaurant?

Yes the owner should be worried, because we are confident that the mean
amount spent per customer is between $36.70 and $40.38. Thus the mean
amount spent per customer is below $45.00.

(c) What sample size would need to be taken to obtain a result which is within $1.00
of the true mean with a probability of 0.95?

2
 Z 2 
2
1.96*7.26 
n  n   202.48 = 203
 e   1

Question 3 is continued on next page

10
Part C

(Please circle your response to each statement)

(i) Regardless of the distribution of the X variable, if the sample size is

True/False
sufficiently large, X has an approximately normal distribution.

(ii) The distribution of the sample mean has the same central location as the
True/False
distribution of the parental population.

(iii) X is a random variable. True/False

(iv) Other things being equal, the confidence interval for the mean will be
True/False
wider for 95% confidence than for 90% confidence.

(v) A population mean is used in the estimation of a confidence interval. True/False

11
 Question 4 (12 + 13 = 25 marks)
Part A
A company is trying out a new marketing plan. Prior to the new campaign, store sales per
week were $5000. The new method is trialled in 15 randomly selected stores. The sample
provided sales figures with a sample mean of $5500 and a standard deviation of $800. Can the
company conclude that the new marketing plan works? Use  = 0.01 and the following
template to answer the question.
HO:  ≤ 5000
H1:  > 5000
Level of Significance: 0.01

Test Statistic and Associated Sampling Distribution:

 is unknown, small sample, assume X~N, hence X ~tn-1.

X 
~ t n1
S
n

Calculation and Decision:

X   5500  5000
t = = 2.42.
S 800
n 15

At 1%, t0.01,14 = 2.62. Since 2.42 < 2.62, we do not reject H0.

Conclusion:

We do not have sufficient evidence to conclude that the new marketing plan
works.

What assumptions need to be made in order to undertake this test?

Assume X ~ N

Indicate the test statistic and p-value on the small sketch below.

Question 4 is continued on next page

12
Part B
A sample of ten developed countries is selected. Information about the percentage labour
force participation in the agricultural sector and the per capita income (in thousands of US
dollars) is obtained. An analysis using EXCEL yielded the information below.
Regression Analysis

Regression Statistics
Multiple R 0.585728146
R Square 0.34307746
Adjusted R Square 0.260962143
Standard Error 1.728871758
Observations 10

ANOVA
df SS MS F Significance F
Regression 1 12.48801956 12.48801956 4.17799591 0.075203745
Residual 8 23.91198044 2.988997555
Total 9 36.4

Coefficients Standard Error t Stat P-value Lower 95% Upper 95%

Intercept 12.52322738 1.995718931 6.275045643 0.00023914 7.92109128 17.12536349
% in Agriculture -0.552567237 0.270334283 -2.044014655 0.075203745 -1.175959212 0.070824738

(a) The independent variable is (please circle)

Income Labour Force in Agriculture (%)

(b) The dependent variable is (please circle)

Income Labour Force in Agriculture (%)

(c) Report the estimated regression equation.

Yˆ  12.52  0.55(% in Agriculture)

b0 = 12.52. If labour force participation is 0 in agriculture, per capita income

is $12, 520.
b1 = -0.55. There is a negative relationship between per capita income and %
labour force participation in agriculture. A 1% in labour force participation
in agriculture, per capita income decreases by $550.

Question 4 is continued on next page

13
 (d) Test whether the regression coefficient β1 is significant at the 10% level of
significance.
HO: ß1 = 0
H1: ß1  0
0.55  0
t  2.04
0.27
t0.05,8 = -1.8595
Since -2.04 < -1.8595, we reject H0. β1 is significant.
p-value = 0.075.
0.075 < 0.10, we reject Ho.

(e) If the percentage of the labour force in agriculture was 10%, what would you
predict the level of per capita income for that country to be?

Yˆ  12.52  0.55(10) = 7.02 $7,020

(f) The value of the coefficient of determination is (please circle)

(i) 0.3431 (ii) 0.5857 (iii) 0.2610

What information does the coefficient of determination provide concerning the

relationship between the variables?

34.31% of variation in per capital income is explained by the model that

contains % labour force participation in agriculture as explanatory
variable.

Comment on the quality of the prediction made in part (e).

The prediction is not good because this regression only explains 34.31% of variation in
per capital income.

14
 FORMULAE

1  2 (X) 2 
X
X
n
S2  X 
n 1  n 
 or S2 
1
n 1
X  X   2

XX
Z
S

P(A') = 1  P(A)

P(A or B) = P(A) + P(B)  P(A and B)

P(A and B) = P(AB) P(B) = P(BA) P(A)

P(AB) = P(A and B) / P(B)

   x P x   2  x 2 P(x)   2
 = np
 2  np1  p
n!
P X   p X 1 p
nX

X! (n  X)!

X
Z


X  X  ps  p
~ N(0 , 12 ) ~ t n1 ~ N(0 , 12 )
 S p(1 p) /n
n n

 S p s (1  p s )
X  Z / 2 X  t( n1) / 2 ps  Z / 2
n n n

Z / 2 2 Z / 2 2 2

1 Z / 2 
n    n   n   .
 e   e  4  e 
p(1 p)
  

b1  1 b0   0
~ t n  2, ~ tn2
Sb1 Sb0

15