Department of Statistics

STAV102

Business Statistics

SEMESTER TEST 1

Date: 24 August 2024 Time: 90 min

Examiner: Dr S Mangisa, Ms S Alexander and Dr L Kepe Marks: 50

Special Instructions:

Part 1: Long Questions Complete the answers on the question paper in the space provided.
25 Marks You may use the back of the pages for rough work.
Follow the instructions given on the multiple choice answer sheet
Part 2: Multiple Choice provided.
25 Marks The use of pencil is preferable.
All multiple choice answers are to be completed on the multiple choice
answer sheet provided.

1. Answer ALL questions.

2. Round off your final answers to 3 decimal places.

3. Only financial/scientific calculators are allowed (no other electronic devices).

4. You may write in pencil (no remarks will be considered in this case).

5. Hand back ALL question papers and answer sheets when finished.

Surname and Initials

Student Number

1
Part 1: Long Questions [24]

Question 1 [5]

A local retail chain is concerned about the efficiency of their checkout process, especially during peak hours.
The management believes that long checkout times could be contributing to a decline in customer satisfaction
and overall sales. To investigate this, they recorded the time (in minutes) it took to complete 14 random
transactions during peak hours over the past week. The data below represent the time (in minutes) for each
of the 14 transactions:
30.5 16.2 18.8 3.5 24.1 57.5 44.6
14.2 22.5 23.5 25.7 29.5 38.4 7.8
(a) Use Sturge’s formula to determine the number of class intervals used in constructing a frequency
distribution table for the data. [1]

(b) Using the result in (a), determine the width of the class intervals. [1]

(c) Using the results you obtained in (a) and (b), complete the following frequency distribution table. [3]

Relative
Number of days Tally Frequency ﴾f ﴿ Percentage
frequency
e

2
Question 2 [13]

A distributor of bottled beverages is concerned about the loss of merchandise due to breakage during transit.
To investigate the extent of the problem, the distributor records the number of cases of beverages which
are damaged during transit each week for a period of one year. The results are presented in the frequency
distribution table below:

Number of cases
Frequency ﴾f ﴿
damaged in transit
e
[0 – 3) 9
e
[3 – 6) 18
e
[6 – 9) 14
e
[9 – 12) 7
e
[12 – 15) 4
(You may use the blank cells in this table to aid in your calculations)

(a) Construct an ogive for the frequency distribution table given above. Clearly label all the axes. [4]

3
(b) Calculate the mean number of cases damaged in transit per week. (You may use the blank cells in the
table above to aid your calculation). [2]

(c) Calculate the standard deviation of the number of cases damaged in transit per week. (You may use
the blank cells in the table above to aid your calculation). [3]

(d) Determine and interpret the 65th percentile of the number of cases damaged in transit per week. [4]

4
Question 3 [6]

Customer satisfaction plays an important role in the success of businesses. Prompt and effective resolutions
to customer complaints can lead to improved customer satisfaction and retention. A local tech company
has noticed a decrease in the number of return/repeat customers. To address this the company sampled
14 recent complaints and recorded how long it took for each complaint to be resolved (in days). The data
below represent the number of days each of the 14 sampled complaints took to be resolved:

32 17 19 3 24 57 44
21 34 23 25 29 38 14

(a) Determine and interpret the median time taken by the tech company to resolve a complaint. [2]

(b) Is there an outlier in the data set. Use statistical reasoning to motivate your answer. [4]

5
Part 2: Multiple Choice Questions [26]

1. The relation between a parameter and a population is the same as the relation between:

a) Descriptive statistics and inferential statistics.

b) A dependent variable and an independent variable.
c) Quantitative and qualitative data.
d) A statistic and a sample.
e) A statistic and a variable.

2. Which of the following does not from part of descriptive statistics?

a) Graphical presentation
b) Confidence Intervals
c) Data collection
d) Organisation of data
e) None of the above
3. Which one of these variables is continuous?
a) The time it takes a randomly selected student to complete an exam.
b) The number of tattoos a randomly selected person has.
c) The number of women taller than 68 cm in a random sample of 5 women.
d) The number of correct guesses on a multiple choice test.
e) None of the above.
4. The temperature (in °C) at an air conditioned room would involve measurement on a(n) _____
scale.

a) nominal
b) ordinal
c) interval
d) ratio
e) None of the above

5. A researcher collects data on the time (in minutes) it takes for customers to complete transactions at
a retail store during peak hours. Which of the following statements about the data is true?
a) The data is on an interval scale, meaning it has a true zero point and allows for meaningful
comparisons of differences between values.
b) The data is on a ratio scale, which means it has no true zero point, but allows for comparisons
of intervals between values.
c) The data is on a ratio scale, meaning it has a true zero point, and allows for meaningful compar-
isons of ratios between values.
d) The data is on an ordinal scale, meaning it only allows for ranking of transaction times but not
for meaningful comparisons of intervals or ratios.
e) None of the above

6
 6. A scientist took daily measurements of the type of wildlife observed, the number of animals observed,
amount of rain and the maximum temperature. Which of the following is a qualitative variable?

a) Type of wildlife
b) Number of animals observed
c) Amount of rain
d) Maximum temperature
e) None of the above

7. Statistical techniques that summarise, organise and simplify data are classified as _______ statist-
ics.

a) Population
b) Sample
c) Inferential
d) Descriptive
e) Classical

For questions (8) to (10) consider the following scenario.

A political party is interested in advertising in a local newspaper and is interested in the proportion of
the community that read the newspaper. In order to assess this, a group of 500 community members were
interviewed and asked whether they read the newspaper. It was found that only 89 of the interviewed
community members read the newspaper.
8. The parameter of interest in this case is:

a) The group of 500 selected community members.

b) The proportion of the 500 selected community members who read the newspaper.
c) The proportion of all community members who read the newspaper.
d) The 89 selected community members who read the newspaper.
e) There is insufficient information to answer this question.

9. The sample of interest in this case is:

a) The group of 500 selected community members.

b) The proportion of the 500 selected community members who read the newspaper.
c) The proportion of all community members who read the newspaper.
d) The 89 selected community members who read the newspaper.
e) There is insufficient information to answer this question.

10. The statistic of interest in this case is:

a) The group of 500 selected community members.

b) The proportion of the 500 selected community members who read the newspaper.
c) The proportion of all community members who read the newspaper.
d) The 89 selected community members who read the newspaper.
e) There is insufficient information to answer this question.

7
 11. A sample of 30 individuals who smoke cigarettes was collected. Each individual was classified according
to how many cigarettes they smoked per day as either a “heavy smoker”, an “average smoker”, a “light
smoker”, or a “social smoker”. 12 of the sampled individuals were classified as “heavy smokers”, 7 as
“light smokers”, 3 as “average smokers” and the rest were classified as “social smokers”. If a pie chart
were to be made for this data, what would be the angle size for the “social smokers” category in the
pie chart?

a) 84°
b) 30°
c) 96°
d) 144°
e) None of the above

For questions (12) to (13) consider the following scenario.

The new manager of the university’s cricket team is interested in learning the primary skills of his new
players. The 24 players of the club were each asked their main area of specialisation: bowling (BO), batting
(BA), wicket-keeping (WK) or fielding (FI). The collected data is given below:

BA WK BA BO BA FI FI FI
BA BO BA BO FI FI BA BA
BO BA WK BO BO BA FI BO

An incomplete frequency distribution table for the data is prepared:

Main area of Relative Size of pie

Frequency (f )
specialisation frequency chart angle
BO 7 0.291
BA 9 0.375
WK 2 0.083
FI 6 0.250

12. Which of the following types of charts is suitable for representing the data?
a) Histogram
b) Ogive
c) Frequency polygon
d) Box-and-whisker plot
e) None of the above
13. Which function would you use to calculate frequencies for the categories in MS Excel?
a) COUNTONLY
b) COUNT
c) TALLYIF
d) COUNT_THESE
e) None of the above

8
For questions (14) to (17) consider the following scenario.
A sales manager at a retail company is analysing the sales performance of their employees over the last
quarter. To improve future sales strategies and identify potential areas for training, the manager took a
random sample of sales figures (in rands) from different employees. The data collected will be used to assess
the effectiveness of current sales techniques and to forecast future performance. The data collected was
organised in an MS Excel spreadsheet, and the output from the MS Excel analysis is given below.

14. What is the range?

a) 807
b) 862
c) 1102
d) 473
e) None of the above
15. What is the sample size?
a) 935
b) 982
c) 473
d) 31285
e) None of the above
16. What is the 4th highest value?
a) 935
b) 982
c) 473
d) 31285
e) None of the above
17. What is the coefficient of variation?
a) 254.146
b) 31.768
c) 51.990
d) 862.000
e) None of the above

9
 18. The data in the histogram below is:

a) Symmetric
b) Positively skewed
c) Negatively skewed
d) Uniformly distributed
e) None of the above

19. Which of these are considered measures of central tendency?

a) Standard deviation, range and mean
b) Mean, median and variance
c) Mode, mean and median
d) Mean, range and variance
e) None of the above
20. One way to measure the spread in data is to calculate the difference between the first and third quartile.
This measure is called the:
a) Midquartile range
b) Interquartile range
c) Differential quartile range
d) Percentile range
e) None of the above

For questions (21) to (22) consider the following scenario.

The length of time between transactions at an ATM is given below (in minutes):
2, 9, 1, 5, 2, 7, 7, 3, 4, 7.
21. Calculate the mean of the data set:
a) 4.2
b) 5.0
c) 5.2
d) 4.7
e) None of the above

10
 22. Calculate the variance of the data set:
a) 2.71
b) 2.57
c) 7.34
d) 6.61
e) None of the above
For questions (23) to (26) consider the following scenario.
“Black Friday” is a Friday in November of each year in which retailers offer many of their products at often
dramatically reduced prices. Originating in the USA, the concept of Black Friday has been adopted by
many retailers in South Africa. To investigate the money spent by individual customers on this day, a large
supermarket collected all the sales made on the day and constructed an ogive for the data.

23. What percentage of customers spent more than R 35 000?

a) 50%
b) 85%
c) 90%
d) 10%
e) 15%
24. What percentage of customers spent less than R 20 000?
a) 40%
b) 54%
c) 72%
d) 60%
e) 46%
25. Estimate the median amount of money spent by a customer.
a) R 15 000
b) R 13 000
c) R 17 000
d) R 10 000
e) R 20 000

11
26. Estimate the 25th percentile of the amount of money spent by a customer.
a) R 15 000
b) R 13 000
c) R 17 000
d) R 10 000
e) R 20 000

12
STAV102 Formula Sheet

( )
ln (n)
k = 1 + 3.3log (n) = 1 + 3.3
ln (10)
xmax − xmin
c =
∑
k
n = fi
fi
Rel. freq =
n
1∑ n
x̄ = xi
n i=1
∑
fi xi
x̄ = ∑
fi
∑ ∑ ∑
2 (xi − x̄)2 x2i − n1 ( xi )2
s = =
n−1 n−1
∑ 1 ∑ 2
fi xi − n ( fi xi )
2
s2 =
n−1
√
∑
(xi − x̄)2
s =
n−1
√∑ ∑
x2i − n1 ( xi )2
s =
n−1
√∑ ∑
fi x2i − n1 ( fi xi )2
s =
n−1
s
CV = × 100
x̄ ( )
c n2 − Fi−1
Me = li +
fi
( )
c (fi − fi−1 )
Mo = li +
(fi − fi−1 ) + (fi − fi+1 )
( )
c n4 − Fi−1
Q1 = li +
fi
( )
c 3n
4 − Fi−1
Q 3 = li +
fi
IQR = Q3 − Q1
LL = Q1 − 1.5 · IQR
U L = Q3 + 1.5 · IQR
( np )
c 100 − Fi−1
Pp = l i +
fi

13