Applied Business Statistics Chapter 3 – Describing Data: Numeric Descriptive Statistics

Exercises This symbol denotes data available online

i The following calculations can be performed either manually, using a calculator, or
using Excel.
1 Identify the central location measure (mean, median, mode) referred to in each
statement.
7 X3.7 – luggage weights
The mass (in kg) of the hand luggage of seven air passengers was as follows:
i
(a) Half of our employees have more than 10 years’ work experience.
11 12 8 10 13 11 9
(b) The most popular city amongst foreign tourists is Cape Town.
(c) The average time taken to complete a task is 18 minutes. (a) Find the average and standard deviation of the hand luggage masses.
2 Which non-central location measure (lower or upper quartile) is described in the (b) Interpret the meaning of each descriptive statistic in (a).
following statement? (c) Find the coefficient of variation of the hand luggage masses.
(d) Is there high relatively variability in the mass of hand luggage between
‘In terms of work experience, 25% of our employees each have more than 15 years
passengers? Explain briefly.
3
of experience.’
For which of the following statements would the arithmetic mean be inappropriate
8 X3.8 – bicycle sales
The number of bicycles sold monthly by a bicycle dealer was:
i
as a measure of central location? (Give a reason.) State which measure of central
location would be more appropriate, if necessary. 25 18 30 18 20 19 30 16 36 24
(a) the ages of children at a playschool
(a) Find the mean and median number of bicycles sold monthly. Interpret each
(b) the number of cars using a parking garage daily
descriptive statistics measure.
(c) the brand of cereal preferred by consumers
(b) Find the range, variance and standard deviation of the number of bicycles sold
(d) the value of transactions in a clothing store
monthly. Interpret the range and standard deviation measures.
(e) the weight of hand luggage carried by airline passengers
(c) Calculate the lower and upper quartiles of monthly bicycle sales. Interpret.
(f) your choice of daily newspaper available in your city
(d) Use the approximate skewness formula to estimate the degree of symmetry in
(g) the responses by citizens on a five-point rating scale to the statement:
the distribution of monthly bicycle sales. Interpret its meaning.
‘South Africa should be divided into two time zones.’
(e) Construct a box plot of monthly bicycle sales. Interpret the plot.
4 Which statements below are true and which are false? Give a reason for your answer.
(f) If the dealer uses the formula ‘mean plus one standard deviation’ to decide on
If the median mass of five parcels for delivery by a courier service is 6.5 kg and one
the opening stock level of bicycles at the beginning of next month, will he
further 7 kg parcel is added to the consignment, then:
run out of stock during the month if he receives orders for 30 bicycles next
(a) the new median mass will be about 6.6 kg
month? Assume no extra bicycles can be ordered.
(b) the median will increase
(c) it is impossible for the new median mass to be less than it was
9 X3.9 – setting times
The setting time for ceramic tile glue is an important quality feature of the product.
i
(d) it is impossible for the new median mass to stay exactly at 6.5 kg
A manufacturer of ceramic tile glue tested a sample of nine batches from a large
(e) the median may increase, but that depends on the actual masses of all five
consignment and recorded the setting times (in minutes) of each batch:
parcels.
5 The following measures of central location were calculated for the number of 27 22 31 18 20 25 21 28 24
people per household in Mossel Bay: mode = 2 people; mean = 4.1 people;
(a) Find the mean and standard deviation of setting times of the ceramic tile glue.
median = 3 people.
(b) How consistent are the setting times across the different batches? Compute the
If there are 9 245 households in the municipal district of Mossel Bay, which of the coefficient of variation as a consistency index measure.
following methods is appropriate to calculate the likely total number of persons living (c) If the consistency index must be less than 10% for the consignment to be
in Mossel Bay? passed by the quality controller, will this consignment be approved for dispatch?
(a) Multiply the number of households by 2. Explain your answer.
(b) Multiply the number of households by 4.1.
(c) Multiply the number of households by 3.
10 X3.10 – wage increases
i
i
A labour consultant analysed the agreed percentage wage increases in 16 wage
6 X3.6 – unit trusts negotiations conducted between labour unions and employers. They were:
The percentage returns last year for seven general equity unit trusts were 9.2;
8.4; 10.2; 9.6; 8.9; 10.5 and 8.3. Calculate the mean and standard deviation of 5.6 7.3 4.8 6.3 8.4 3.4 7.2 5.8
percentage returns. 8.8 6.2 7.2 5.8 7.6 7.4 5.3 5.8

104 105
Applied Business Statistics Chapter 3 – Describing Data: Numeric Descriptive Statistics

(a) Find the mean and median negotiated percentage wage increases. (a) Find the average and standard deviation of the percentage of bad debts
(b) Find the variance and standard deviation of the percentage wage increases. amongst the 17 furniture retailers surveyed.
(c) Compute two standard deviation limits about the mean. Interpret these. (b) Find the median percentage of bad debts amongst the 17 furniture retailers
(d) How consistent are the percentage wage increases agreements? Compute the surveyed.
coefficient of variation as a consistency index measure. (c) Interpret the findings from (a) and (b).
11 Two groups of bank trainees each wrote a banking exam with the following (d) Is there a modal percentage of bad debts? If so, identify it and comment on its
percentage results: usefulness.
(e) Calculate the skewness coefficient for percentage of bad debts. Is the data
Mean Variance Sample size
skewed?
Group 1 76 110 34 (f) Compute the first quartile and the third quartile of the percentage of bad debts
Group 2 64 88 26 amongst the furniture retailers surveyed. Interpret these quartile values.
(g) The chamber of business monitors bad debt levels and will advise an industry
(a) Compute the coefficient of variation of exam scores for each trainee group.
to take corrective action if the percentage of bad debts, on average, exceeds 5%.
(b) Which group showed greater consistency in exam score performance? Why?
Should the chamber of business send out an advisory note to all furniture
12 X3.12 – meal values
i retailers based on these sample findings? Justify your answer.
A restaurant owner randomly selected and recorded the value of meals enjoyed
by 20 diners on a given day. The values of meals (in rand) were:
15 X3.15 – fish shop
A fish shop owner recorded the daily turnover of his outlet for 300 trading days
i
44 65 80 72 90 58 44 47 48 35 as shown in the frequency table.
65 56 36 69 48 62 51 55 50 44
Daily turnover Number of days
(a) Define the random variable and its data type. 500  – < 750 15
(b) Compute the mean and standard deviation of the value of meals at the restaurant. 750  – < 1 000 23
(c) What is the median value of a meal at the restaurant? Interpret its meaning.
1 000  – < 1 250 55
(d) What meal value occurs most frequently?
1 250  – < 1 500 92
(e) Which central location measure would you choose? Why?
13 X3.13 – days absent
The human resources department of a company recorded the number of days
i 1 500  – < 1 750
1 750  – < 2 000
65
50
absent of 23 employees in the technical department over the past nine months: (a) Compute and interpret the (approximate) average daily turnover of the fish shop.
(b) Find the median daily turnover of the fish shop. Interpret its meaning.
5 4 8 17 10 9 30 5 6 15 10 9
(c) What is the modal daily turnover of the fish shop?
2 16 15 18 4 12 6 6 15 10 5
(d) Find the maximum daily turnover associated with the slowest 25% of trading
(a) Find the mean, median and modal number of days absent over this nine-month days.
period. (e) What daily turnover separates the busiest 25% of trading days from the rest?
Interpret each central location measure.
(b) Compute the first quartile and the third quartile of the number of days absent.
16 X3.16 – grocery spend
An economist conducted a study to identify the percentage of family income i
Interpret these quartile values for the human resources manager. allocated to the purchase of groceries. She surveyed a random sample of 50 families
(c) The company’s policy is to keep its absenteeism level to within an average and compiled the following numeric frequency distribution:
of one day per employee per month. Based on the findings in (a), is the
company successful in managing its absenteeism level? Explain. Percent of income Number of families
14 X3.14 – bad debts
The Gauteng chamber of business conducted a survey amongst 17 furniture i 10 – under 20%
20 – under 30%
6
14
retailers to identify the percentage of bad debts in each company’s debtors’ book. 30 – under 40% 16
The bad debts percentages are as follows: 40 – under 50% 10
50 – under 60% 4
2.2 4.7 6.3 5.8 5.7 7.2 2.6 2.4 6.1 6.8
2.2 5.7 3.4 6.6 1.8 4.4 5.4

106 107
Applied Business Statistics Chapter 3 – Describing Data: Numeric Descriptive Statistics

(a) Compute and interpret the (approximate) mean percentage of family income
allocated to grocery purchase. 22 X3.22 – veal dishes
The price of a veal cordon bleu meal (in rand) was taken from the menus of
i
(b) What is the maximum percentage of income that is allocated to grocery purchase by:
(i) the lower 50% of families? 28 Durban restaurants in a survey conducted by Lifestyle magazine into the cost of
(ii) the lower 25% of families? ‘dining out’. The prices are:
(c) 25% of families spend more than a specific percentage of their income on
48 66 60 90 58 68 53 63 64 55 64 58 54 72
groceries. What is that percentage of income value?
17 X3.17 – equity portfolio
Find the average price paid per share in an equity portfolio consisting of:
i 56 80 55 62 75 48 55 45 48 72 52

Use Excel’s Data > Data Analysis > Descriptive Statistics option and, where
68 56 70

40 shares bought for R15 each; 10 shares bought for R20 each; 5 shares bought for necessary, the function keys QUARTILE.EXC and PERCENTILE.EXC, to answer the
R40 each; and 50 shares bought for R10 each. Use the weighted average formula. following questions:
18 X3.18 – car sales
Value Cars, a pre-owned car dealership with branches throughout Gauteng,
i (a) Define the random variable and its data type.
(b) Find the mean and median price of a veal cordon bleu meal. Interpret each
last month sold 5 cars at R25 000 each; 12 cars at R34 000 each; and 3 cars at
measure.
R55 000 each. What was the average price per car sold by Value Cars last month?
(c) Can you identify a modal price? Give its value and discuss its usefulness.

19
Use the weighted average formula.
X3.19 – rental increases i (d) Identify the value of the standard deviation of the price of veal cordon bleu.
(e) Compute the skewness coefficient. Does the data appear to be skewed? If so,
Office rental agreements contain escalation clauses. For a particular office complex
why?
in the Nelspruit CBD, the escalation rates based on the previous year’s rental over
(f) Which central location measure would you choose to report in the article on
four years were 16%, 14%, 10% and 8% respectively.
‘dining out’? Why?
Use the geometric mean to find the average annual escalation rate in office rentals for
(g) What is the least price that a patron to one of these restaurants would pay if
20
this office complex over the four-year period.
X3.20 – sugar increases i they dined out at any one of the most expensive 25% of restaurants?
(h) The least expensive 25% of restaurants do not charge above what price for the
The price of a kilogram of sugar increased by 5%, 12%, 6%, 4%, 9% and 3%
over the past six years. veal cordon bleu meal?
(a) Find the average annual percentage increase in the price of sugar (per kg) using (i) What is the least price to be paid for the most expensive 10% of veal cordon
bleu meals?
i
the geometric mean.
(b) Why is the geometric mean more suitable than the arithmetic mean? 23 X3.23 – fuel bills
21 X3.21 – water usage
Thirty households in a Paarl suburb were surveyed to identify their average
i The monthly fuel bills of a random sample of 75 Paarl motorists who commute
to work daily by car were recorded in a recent survey.
water usage per month (in kilolitres, kl). The usage per household was: (a) Use the Descriptive Statistics module in either Data Analysis or X-Static to find
the mean, median, variance, standard deviation and skewness coefficient of the
10 18 30 13 42 14 9 15 19 20 monthly fuel bill of the sample of car commuters.
25 15 24 12 15 16 22 22 8 33 (b) Interpret the meaning of each descriptive statistic in (a).
50 26 16 32 25 26 16 26 25 12 (c) Is the data skewed? If so, in what direction? What would be the cause of
skewness?
Use Excel’s Data > Data Analysis > Descriptive Statistics option and, where (d) Find the coefficient of variation for monthly fuel bills. Is the relative variability
necessary, the function key QUARTILE.EXC to answer the following questions: between the sampled motorists’ monthly fuel bills low?
(a) Find the mean, median and modal water usage across the 30 households. (e) Use the Excel function key QUARTILE.EXC to find the lower and upper quartiles
(b) Find the variance and standard deviation of water usage per household. of monthly fuel bills of motorists. Interpret each quartile.
(c) Find the first and the third quartile of water usage amongst the 30 households. (f) Compile the five-number summary table for monthly fuel bills.
(d) Interpret the findings from (a) to (c) for the municipal officer who conducted (g) Construct a box plot of monthly fuel bills.
this survey. (h) Describe the profile of the monthly fuel bills of Paarl motorists who use their
(e) If there are 750 households in the Paarl suburb, what is the most likely total cars to commute daily to work and back.
water usage (in kl) amongst all these households: (i) Assume that the cost of fuel is R10 per litre and that there are 25 000 motorists
(i) in a month? who commute to work daily in Paarl by car. Estimate the most likely total
(ii) in a year? amount of fuel used (in litres) by all car commuters in Paarl in a month.

108 109
Applied Business Statistics Chapter 3 – Describing Data: Numeric Descriptive Statistics

24 X3.24 – service periods

The Association of Professional Engineers recently surveyed a sample of 100
i (h) What was the minimum dividend yield declared by the top 10% of JSE
companies? (Hint: Use the PERCENTILE.EXC function key.)
(i) What percentage of JSE companies did not declare more than a 3.5% dividend
of its members to identify their years of experience.
yield last year? (Hint: Compute the cumulative frequency distribution to find the
(a) Use the Descriptive Statistics module in either Data Analysis or X-Static to find
cumulative percentages.)

i
the mean, median, standard deviation and skewness measure of the years of
26 X3.26 – rosebuds
experience for the sample of professional engineers.
A commercial flower grower in Hazyview sells fresh-cut rosebuds to retailers in
(b) Interpret the meaning of each descriptive statistical measure in (a).
Johannesburg. The unit price per rosebud (in cents) varies according to supply and
(c) Use either the Histogram option in Data Analysis or the Summary Tables and
demand. The grower has recorded the unit selling price for 100 transactions over the
Graphs module in X-Static to compute a frequency distribution and a histogram
past two months.
of the years of experience for the sample data. (Hint: Use the bin range given in
(a) Define the random variable and data type.
the database.)
(b) Use the Descriptive Statistics module in either Data Analysis or X-Static to find
(d) Compute an interval for the years of experience of professional engineers that
the mean, standard deviation, median and skewness coefficient descriptive
covers one standard deviation either side of the sample mean.
measures of the unit selling price of rosebuds.
What percentage of the sampled professional engineers does this represent?
(c) Compute and interpret the coefficient of variation of the unit selling price of
(e) The Association of Professional Engineers would like to see a mix of
rosebuds.
‘experience’ and ‘new blood’ amongst its members. Ideally they would like to
(d) Use Excel’s function key QUARTILE.EXC to compute the upper and lower
have at least 20% of their members with less than three years of experience (i.e.
quartiles of the unit selling price of rosebuds.
‘new blood’ members) and at least 20% of their members with more than
(e) What the highest unit selling price for the cheapest 25% of transactions?
12 years of service (i.e. ‘experienced’ members). Based on the histogram
(f) What was the minimum unit selling price received for the highest priced 25%
and frequency distribution in (c), is this desired mix of experience being
of transactions?
achieved? Comment.
i
(g) What was the lowest unit selling price received for the highest-valued 10% of
25 X3.25 – dividend yields
transactions?
A survey of 44 JSE-listed companies recorded their dividend yields (as a
(h) What was the highest unit selling price received for the lowest-valued
percentage) for last year as shown in the following table:
10% of transactions? (Hint: For (g) and (h) use the Excel function key
5.3 4.8 3.1 4.1 6.1 4.1 3.2 4.6 7.6 1.6 PERCENTILE.EXC.)
4.6 1.9 4.8 2.9 1.5 5.1 2.8 3.6 3.3 5.5 (i) Construct the five-number summary table and draw a box plot. Interpret the
2.8 4.2 3.6 3.1 5.9 2.9 3.6 4.1 4.9 2.7 profile of the unit selling price of rosebuds for the flower grower.
3.7 7.1 6.2 2.8 5.1 3.8 3.4 3.9 5.8 6.3
6.8 4.3 5.1 5.4

(a) Define the random variable and its data type.

(b) Use the Descriptive Statistics module in either Data Analysis or X-Static to find
the mean, median, mode, standard deviation and skewness measure of the
dividend yields of the JSE-listed companies.
(c) Interpret the meaning of each descriptive statistical measure in (b).
(d) Which central location measure would you use to report on the dividend yields
of companies? Why?
(e) Use either the Histogram option in Data Analysis or the Summary Tables and
Graphs module in X-Static to compute a numeric frequency distribution and a
histogram of the dividend yields of the sampled JSE companies. (Hint: Use the
bin range given in the database.)
(f) Use Excel’s function key operations (MIN, MAX, MEDIAN and QUARTILE.EXC)
to compute the five-number summary table.
(g) Construct a box plot of the dividend yields of the JSE-listed companies and
interpret the profile of the dividend yields declared by JSE companies last year.

110 111