Measures of Central Tendency (集中趨勢的量度)

Part 1: Concept and Example

1. Three averages: mean, median, mode

Measures of central tendency are summary statistics that represent the centre point or
typical value of a dataset. In our daily life, we often want to use one specified value to
represent or summarize a set of data, because this value often can show the central
tendency of data set.

There are three values which can represent or summarize a set of data. They are mean,
median and mode. These three values are called averages (平均值) in statistics, and
they are used to measure the central tendency of a set of data. Each of them can
represent the rough distribution of the set of data effectively (i.e., give comments about
the overall results of the set of data). For example, Peter is a S3A student. In a
Mathematics test, he gets 70 marks. He wants to compare his score with other
classmates and wants to know the overall results of the students in the test. In this case,
he needs the measures of the central tendency, i.e. find the mean, median and mode of
the marks of all S3A students.

Let’s take a quick look at these three averages.

Mean Median Mode
(the average value) (the middle value) (the most frequent value)
Data: 1, 6, 8, 9, 12 Data:13,11,18,23,20 Data: 17,36,26,17,15

Mean : the sum of all data Median: arrange data in Mode: the datum that
divided by the total order and pick the occurs the most frequently
number of data. middle value.
11,13,18,20,23
Mean =(1+6+8+9+12)/5 Median = 18 Mode = 17
=7.2

Note: The word average is used loosely in our daily life. However, it has a precise
meaning (i.e. a measure of central tendency of a set of data) in statistics.

Page 1 of 37
2. Finding the Averages for Ungrouped Data

2.1 Mean (平均數)

The mean (also called arithmetic mean) is the most commonly used average in our
daily lives to measure the central tendency of a set of data. It can often be found in
newspapers and magazines, eg the mean of daily temperature of Hong Kong in a
month.

The mean of a set of ungrouped data is equal to the sum of all data divided by the total
number of data.

We usually denote the mean by the symbol 𝑥̅ (read as bar x).

̅)= Sum of all data / Total number of data
Mean (𝒙

Thus, for a set of n data 𝒙𝟏 , 𝒙𝟐 , 𝒙𝟑 , …., 𝒙𝒏 ,

̅) = (𝒙𝟏 + 𝒙𝟐 + 𝒙𝟑 + … +𝒙𝒏 ) / n
mean (𝒙

Example: Find the mean of 1, 6, 8, 9, 12.

Solution:
Mean = (1+6+8+9+12)/5 = 36/5=7.2
Remarks: The mean is not necessarily one of the data.

Example: The mean of five numbers 10,11+a,9, 20-a and 18+a is 14.
Find the value of a.
Solution:
10 + (11+a) + 9 + (20-a) + (18+a)/5 = 14
68 + a = 14 x 5
68 + a = 72
∴ a=2

Page 2 of 37
If there are extreme values (extremely large or extremely small) in the data set, mean
may not be appropriate to use to reflect the central tendency of the data set (i.e. in
such cases, mean may not clearly show the central tendency of a set of data).

For example:
Case 1: there is an extremely large datum in a set of data.
Data set: 1,2,3,4, 100
Mean = (1+2+3+4+100) / 5 = 22
There is an extremely large datum ‘100’ in the data set. As a result, we find the mean
‘22’ which is larger than most of the data.
Therefore, the mean cannot reflect the central tendency of the set of the data.
Case 2: there is an extremely small datum in a set of data.
Data set: 1, 1002,1003, 1004,1005
Mean = (1 + 1002 + 1003 + 1004 + 1005) / 5 = 803
There is an extremely small datum ‘1’ in the data set. As a result, we find the mean
‘803’ is smaller than most of the data.
Therefore, the mean cannot reflect the central tendency of the set of the data.

Page 3 of 37
2.2 Median (中位數)

The median is another commonly used average that measures the central tendency of
a set of data. It is used widely in research by Statistics Department. For example, the
median monthly salary of all employees in a Hong Kong and the median age of the
population in Hong Kong, etc.

The median is the value in the middle of a set of data when the data are arranged in
ascending order or descending order.

We can find the median by the following steps:

1. Arrange the data in ascending order or descending order.
2a. If the total number of data (n) is an odd number, the median is the value of the
middle datum.
n +1
Median = the ( )th datum
2

2b. If the total number of data (n) is an even number, the median is the mean of the
values of the two middle data.
1 𝑛 𝑛
Median = [the th datum + the( + 1)th datum]
2 2 2

The advantage of using median is that the central tendency is not affected by extreme
value (extremely large values and/or extremely small values) in the data set, because
it only shows the middle value of a set of data. However, if the given data set involves
a large number of data, then it can be time-consuming to arrange the data in
ascending order or descending order

Page 4 of 37
Example: Find the median of each of the following sets of data
(a) 13,11,18,23,29,40,20
(b) 20,13,23,50,29,39,18,45

Solution
(a) Arranging the data in ascending order: 11,13,18,20,23,29,40
There are 7 data, so total number of data is an odd number.
7+1
∴ Median = the th datum
2

= the 4th datum

= 20
(b) Arranging the data in ascending order: 13,18,20,23,29,39,45,50
There are 8 data, so total number of data is an even number.
1 8 8
Median = [the th datum + the( + 1)th datum]
2 2 2

1
= (the 4th datum + the 5th datum)
2

1
= (23+29)
2

= 26

Example: The mean of five numbers 1, y, 12, 6 and 8 is 7.2.

(a) Find the value of y.
(b) Find the median of this set of data.
Solution
(a) (1+y+12+6+8)/5 =7.2
27+y = 7.2 x 5
27+y = 36
∴ y=9
(b) Arranging the data in ascending order: 1, 6, 8, 9, 12.
There are 5 data, so total number of data is an odd number.
5+1
∴ Median = the th datum
2

= the 3th datum

=8
Page 5 of 37
2.3 Mode (眾數)

The mode of a set of data is the datum that occurs the most frequently.

As the number of occurrences of a datum is called frequency, we can also

say that the mode of a set of data is the datum with the highest frequency.

The mode is used especially when we want to use one of the data in the data set as
the measure of central tendency. For example, the mode of the sizes of shoes in a
shop.

The mode is not affected by extreme values. However, if the given data set has only
very few data equal to the mode, the mode may not reflect the central tendency of
the data set.

For example:
there is an extremely large datum in a set of data.
Data set: 3,3, 4, 5, 6, 7, 8, 9,10,11
Mode = 3
There is only 2 out 10 data are equal to the mode
As only very few data are equal to ‘3’ and ‘3’ is the smallest value in the data set, the
mode cannot reflect the central tendency of the set of the data.

Note:
(a) If two (or more) data have the same highest frequency, then all of them are the
modes of the set of data, i.e., there may be more than one mode in a set of data.

(b) If all the data have the same the frequency, then there is no mode in this set of
data.

(c) When the data are not numbers (eg favourite colour, hobbies etc), only the mode
can be used to reflect the central tendency of data set. In such case, mean or median
are not applicable or cannot be calculated.

Page 6 of 37
Example: Find the mode of each of the following sets of data.
(a) 175,363,265,175,120.
(b) 21,27, 32,32,32,32,32,53,53,64,64,64,64,64,25
(c) 34,34, 56,56,78,78

Solution
(a) In this data set, 175 cm occurs twice. It is the datum with the highest frequency.
∴ Mode = 175

(b) In this data set, 32 and 64 each occurs 5 times. Both of them are data with the
highest frequency.
∴ Modes = 32 and 64.

(c) In this data set, 34,56,78 175 each occurs twice. All the data have the same the
frequency,
∴ There are no modes in this set of data.

Example: The following table shows the numbers of correct answers made by
some students in a test.
Number of correct answers 5 6 7 8 9 10
Number of students 3 6 10 10 4 2
Find the mode of the number of correct answers made by of students.

Solution:
∵ The highest frequency is 10.
∴ The modes are 7 and 8.

Example: The mode of the nine numbers 20, 13, 9, x+2, 10, 9, 17,21 and y+3 is 10.
Find the values of x and y.

Solution
Since the frequency of the datum 9 is two while the mode of this set of data is 10, the
frequency of 10 must be more than two. Thus, x+2 and y +3 must be equal to 10.
x+2=10, y+3=10
∴ x=8, y=7

Page 7 of 37
3. Finding the Averages for a Large Set of Discrete Data
For a large set of discrete data where many data have the same value, it is
inconvenient to obtain the mean by adding the data individually. We can organize the
data in a frequency distribution table. Based on this table, we can calculate the mean.

(i) The mean be calculated by the following formula:

Mean (𝒙 ̅)= Sum of the products of datum times corresponding frequency/Sum of
frequency

If the data 𝒙𝟏 , 𝒙𝟐 , 𝒙𝟑 , …., 𝒙𝒏 have frequencies 𝒇𝟏 , 𝒇𝟐 , 𝒇𝟑 , …., 𝒇𝒏 respectively, then

̅)= sum of xf / sum of f
mean (𝒙
̅)= (𝒙𝟏 𝒇𝟏 + 𝒙𝟐 𝒇𝟐 + 𝒙𝟑 𝒇𝟑 + …. +𝒙𝒏 𝒇𝒏 ) / ( 𝒇𝟏 + 𝒇𝟐 + 𝒇𝟑 + …. +𝒇𝒏 )
mean (𝒙

(or, ̅) =
mean (𝒙 )

(ii) The median can be obtained from the data in the middle of the frequency
distribution table.

(iii) The mode can be obtained from the data with the highest frequency in the
frequency distribution table.

Page 8 of 37
Example: There are 14 boys and 16 girls in S3A. The mean weights of the boys and
girls are 50 kg and 46 kg respectively. Find the mean weight of the whole class, correct
to the nearest integer.

Solution
Mean weight of the whole class
𝟏𝟒 𝒙 𝟓𝟎+𝟏𝟔 𝒙 𝟒𝟔
=
𝟏𝟒+𝟏𝟔
= 48 kg (cor. to the nearest integer)

Example: The number of times that students in class 1C were late last month are
shown below.

Number of times Frequency (f)

getting late (x)
0 13
1 10
2 5
3 4
4 2
5 1
Find (a) the mean, cor. to 2 d.p. (b) the median, (c) the mode of this set of data.

Solution
(a) Mean= (0x13+1x10+2x5+3x4+4x2+5x1)/(13+10+5+4+2+1)
= 45/35
= 1.29 (cor. to 2 d.p.)
Note: the mean may not be an integer.

(b) Total frequency=13+10+5+4+2+1=35

Median = the middle datum (i.e., the 18th datum)

=1
(c) Since the most frequent number of times the students were late is 0.
∴ Mode = 0

Page 9 of 37
4. Finding the Averages for Grouped Data

Assume we are given below data of the waiting time of 50 passengers (correct to the
nearest minute).
Waiting time class mark Frequency
(min) (min)
1-3 2 5
4-6 5 10
7-9 8 18
10-12 11 13
13-15 14 4

The above data allows us to find the averages.

(1) Mean
If the class marks of the intervals are 𝒙𝒊 , and their corresponding frequencies are 𝒇𝒊
then the following formula can be used to calculate the mean:
Mean (𝒙 ̅)= Sum of 𝒙𝒊 𝒇𝒊 /Sum of 𝒇𝒊

∴ The mean of the waiting time of above 50 passengers

= (2x5+5x10+8x18+11x13+14x4)/(5+10+18+13+4)
= 403/50
=8.06

Note: When the data are grouped into intervals, the mean obtained using class marks
is an approximate value only. It is because we have not considered each original
datum in the data set in calculating the mean. However, this approximation is
acceptable when the number of data is large, since the mean obtained is good enough
to show the central tendency of the data. At the same time, the calculation in this way
saves a lot of time.

Note: For the same set of data, the mean of a grouped data (分組數據) is affected by
how the data are grouped. (i.e., different grouping of classes may obtain different
mean.)

Page 10 of 37
(2) Median

The median of a set of grouped data can be found from the cumulative frequency
polygon or cumulative frequency curve constructed.
𝑛
Median = the th datum from the corresponding cumulative frequency polygon or
2
cumulative frequency curve.

Step1: Construct cumulative frequency table using the frequency distribution table.
Then, draw cumulative frequency polygon or cumulative frequency curve using
cumulative frequency table.

The cumulative frequency table and the cumulative frequency curve of the waiting
time of 50 passengers are shown as follows.
(i) Cumulative frequency table
Waiting time less than (min) Cumulative frequency
0.5 0
3.5 5
6.5 15
9.5 33
12.5 46
15.5 50

(ii) Cumulative frequency curve

Waiting time of 50 passengers

50
Cumulative frequency

40

30

20

10

0
0 2 4 6 8 10 12 14 16 18

Waiting time (min)

Page 11 of 37
Step 2: Find the total frequency (n) of the grouped data. Locate the position of half of
the total frequency from the vertical axis (i.e. n/2). The median is the corresponding
value on the horizontal axis.

Half of the total frequency is 50/2. i.e. 25. On the horizontal axis, the value
corresponding to the cumulative frequency of 25 is 8.2.
∴ Median = 8.2 min

Note: The value obtained from the cumulative frequency polygon (or curve) is only an
approximation. Its value is affected by how we group the data. (I.e. the grouping
method).

Note: According to the definition, we should consider the two different cases:
total number of data (n) is odd or even using different methods to find the median.
However, when n is large, the median will be very close to the (n/2)th datum no
matter whether n is odd or even. Hence for convenience, we may read the (n/2)th
datum from the graph and take it as a good approximate value for the median.

Page 12 of 37
(3) Modal Class

When the data are grouped into intervals, we know the number of data in each group,
but we do not know the frequency of each original datum. Therefore, we cannot find
the most frequent data (i.e. the mode) from data grouped in class intervals. In this
case, we can find the modal class (眾數組) instead.

In a frequency distribution table, the class interval with the highest frequency is
defined as a modal class. In a histogram, the class with the tallest bar is the modal
class.

Modal class is a popular average in our daily life. For example, a shoe manufacturer
obviously will produce shoes that suits most of the people.

Different grouping of class intervals will result in a different modal class.

Like the mode, there may be no model class or more than one model class.
That is,
(a) If the frequencies of all the class intervals are the same, then there is no modal
class of the data set.
(a) If two or more class intervals have the same highest frequency, then all of them
are the modal classes of the data set.

Example: Assume we are given below data of the waiting time of 50 passengers.
(correct to the nearest minute)
Waiting time (min) Frequency
1-3 5
4-6 10
7-9 18
10-12 13
13-15 4
Find the modal class of the waiting time of these passengers.

Solution
The class interval 7-9 has the highest frequency (18), thus modal class is 7-9.

Page 13 of 37
5. Uses and Abuses of Averages

5.1 Uses of Averages

Not all the averages (mean, median and mode) are suitable to reflect the central
tendency of a data set or compare two sets of similar data. If we want to use them
effectively, we should choose an appropriate one in different situations carefully.

Characteristics of the three averages are as follows.

Mean 1. All the data are involved when we calculate the mean.
2. The mean is the most commonly used average, especially in the
situations not involving distortion by extreme values.
3. If there are extreme values (extremely large or extremely small) in the
data set, mean may not be appropriate to use to reflect the central
tendency of the data set.
4. Example: the mean can be used to measure central tendency of waiting
times of passengers for buses, the monthly rainfall of a city , daily
temperature of a city and so on.
Median 1. The median is a measure of central tendency that is not affected by
extreme values (too big or too small).
2.It is the value in the middle of a set of data when the data are arranged
in ascending or descending order.
As we need to arrange the data in ascending or descending order first,
it may be quite time-consuming when finding the median.
3. Example: the median can be used to measure central tendency of the
salaries of employees in Hong Kong, family income in a country and so on.
Mode 1. The mode (or the modal class) represents data which occur most
frequently.
2. Mode (or the modal class) is not affected by extreme values.
3. Mode (or the modal class) may not lie close to the middle of a data set.
4. Sometimes the mode may not exist, or it may not be unique.
5. Example: the mode can be used to measure central tendency of the
shoe sizes (e.g. which size shoes should be produced more?), model age
groups of citizens in a country (used as a reference for government
planning) and so on.

Page 14 of 37
Summary for the three averages
Characteristic Mean Median Mode
1. It always exists ✓ ✓ X

2. It must be a unique value ✓ ✓ X

3. It must be one of the data (ungrouped data) X X ✓

4. All the data are involved in the calculation ✓ X X

5. It is affected by an extreme datum ✓ X X

6. All data should be arranged in order before X ✓ X

calculation
7. it can be obtained from a graph X ✓ ✓

In statistics, the mean, median, and mode are the three most common measures of
central tendency. Using these measures in everyday life involves not only
understanding the differences between them, but also which one is appropriate for a
given situation. Each one calculates the central point using a different method.
Choosing the best measure of central tendency depends on the type of data you have.

As there are different characteristics and limitations of mean, median and mode, we
need to consider carefully which average is more appropriate in different situations.

Sometimes, there is only one average which is suitable for a set of data. For example,
a manufacture would like to know what size of shoes must be produced (the size of
shoes which has maximum demand). Here mode is the most appropriate average
because it is repeated the highest number of times in the series. In this case, the
mean and median are meaningless.

Page 15 of 37
Comparison of Two Sets of Data by Using Averages

Sometimes, we can use appropriate averages to compare two sets of data of the same
nature.

For example, the following table shows the average monthly salaries of the employees
of companies A and B (correct to the nearest hundred dollars).
Mean monthly Median monthly Modal monthly
salary salary salary
Company A $14000 $14500 $13800
Company B $13000 $14000 $13100

From the above table, we can see that the three averages of company A are all higher
than those of company B. We can say the salary level of employees of company A is
higher than that of company B in general.

However, if the three averages of a set of data are not consistently all higher (or
lower) than those of the other set, then we can only draw a less probable conclusion.
In this case, we will have to decide whether there is a more appropriate average for
comparison or not.

Page 16 of 37
5.2 Abuses of Averages

Statistics plays an important role in our daily lives. Government and organization
widely used statistical measures to make decisions and do strategic planning.
However, some people may use inappropriate averages to mislead the readers to
achieve their purpose or use unreasonable calculations to work out the averages to
distort the reality in their favour. Therefore, we should have a clear understanding on
the concept of statistical measures to avoid any misinterpretation. Otherwise, we may
incur losses.

Below is an advertisement of a trading company:

Shipping Clerk Wanted

--Recording order details on the computer system

--Labelling package with all vital information
--Monitoring inventory and ordering more units as needed
--At least 3 years’ experience.
-- Average monthly salary is $ 13,000.

It is given that there are ten employees in this company. Their monthly salaries are as
follows: $10,000, $10,100, $10,200, $10,300, $10,400, $10,500, $10,600, $10,700,
$ 13,000, $ 13,000.

Let us find the three averages.

Mean of monthly salaries = ($ 10,000 + $ 10,100 + $ 10,200 + $ 10,300 + $ 10,400
+$ 10,500 + $10,600 + $10,700 + $ 13,000 + $ 13,000)/10 =$10,880
Median of monthly salaries = ($ 10,400 +$ 10,500)/2=$10,450
Mode of monthly salaries =$13,000

In this case, the company use the mode as an average in the advertisement. However,
there are only 2 employees who monthly salary are equal to $13,000 and the other 8
employees who monthly salary are much lower than $13,000. The average used in
the advertisement does not reasonably reflect the central tendency of the monthly
salaries of employees in the company. Therefore, it misleads the public.

Page 17 of 37
Example: The table below shows the monthly salaries of 10 employees in a company.
Monthly $ 10,000 $ 10,200 $ 10,400 $10,600 $30,000
salary
Number of 1 2 4 2 1
employees

The company claims that the average salary of employees is $ 12,320.

(a) Which average is used by the company?
(b) Do you think the average used by the company can reasonably reflect the central
tendency of the monthly salaries of employees in the company? Explain your answer.

Solution:
(a) Mean of the monthly salaries
= ($10,000 x1 +$10,200×2+$10,400×4+$10,600×2+$30,000)/10
= $12,320

Median of the monthly salaries = $10,400

[Note: There are 10 data. The median is the mean of the 5 th ($10,400) and
the 6th ($10,400)]

Mode of monthly salaries = $10,400

∴ The mean is used by the company.

(b) The mean is affected by the extreme value ($30,000). Therefore, it cannot
reasonably reflect the central tendency of the monthly salaries of employees in the
company.

Page 18 of 37
6. Effects of Changing Data on Averages

In our daily life, sometimes we may need to modify a set of data by adding or
multiplying a common constant and see the effects of this change on the central
tendency. For example, (i) as times passes, the ages of a family members will increase
by a common constant, (ii) the salaries of the employees in a company increase by
the same percentage. How will these changes affect the central tendency?

In other words, if there is a change to a set of data, what will be the effects on the
three averages (i.e. the mean, median and mode)?

(1) Adding a Common Constant to Each Datum

̅, median p and mode q, if a common constant k is added
For a set of data with mean 𝒙
to each datum, then
the new mean = 𝒙 ̅+𝒌
the new median = p + 𝒌
the new mode = q + k

Note: The above value of k can be any positive number, negative number or 0.

(2) Multiplying Each Datum by a Common Constant

̅, median p and mode q, if each datum is multiplied by a
For a set of data with mean 𝒙
common constant k, then
the new mean =k 𝒙 ̅
the new median = kp
the new mode = kq
Note: The above value of k can be any positive number or negative number.

(3) Dividing Each Datum by a Common Constant

̅, median p and mode q, if each datum is divided by a
For a set of data with mean 𝒙
common constant k (where k≠0), then
the new mean = ̅𝒙 ÷ k
the new median = p ÷ k
the new mode = q ÷ k
Note: The above value of k can be any positive number or negative number .

Page 19 of 37
Example: The mean, median and mode of a set of data are 50, 60 and 70 respectively.
(a) If 5 is added to each datum, find the new mean, new median, and new mode of
this data set.
(b) if each datum is multiplied by 1.2, find the new mean, new median, and new mode
of this data set.
(c) if each datum is divided by 2, find the new mean, new median, and new mode of
this data set.

Solution
(a) New mean=50+5=55
New median=60+5=65
New mode=70+5=75

(b) New mean=50×1.2=60

New median=60×1.2=72
New mode=70×1.2=84

(c) New mean=50 /2=25

New median=60 /2=30
New mode=70 / 2=35

Page 20 of 37
7. Weighted Means (加權平均數)

In statistics, a weight (權數) is defined as the degree of importance for each datum.
That is, it is a coefficient assigned to each datum in a computation to make the
number's effect on the computation reflect its importance. The larger the weight, the
more importance the corresponding datum is.

We have learnt that Mean (𝒙̅) = (𝒙𝟏 + 𝒙𝟐 + 𝒙𝟑 + … +𝒙𝒏 )/n.

In this formula, we assume that each datum has the same importance (i.e., same
weight).

However, in some situation, there is a need to assign different importance to each

datum. For example, the importance of the marks for Test, Mid-term examination,
Final examination of Mathematics in school are difference. For more important items,
they are assigned larger weight. For the less important items, they are assigned smaller
weight. Then we find the weighted mean by using below formula.

Weighted mean = sum of each datum multiplies by its weight/sum of the weights

For a set of data 𝒙𝟏 , 𝒙𝟐 , 𝒙𝟑 , …., 𝒙𝒏 with weights 𝒘𝟏 , 𝒘𝟐 , 𝒘𝟑 , …., 𝒘𝒏 respectively,

then weighted mean
= sum of xw / sum of w
= (𝒙𝟏 𝒘𝟏 + 𝒙𝟐 𝒘𝟐 + 𝒙𝟑 𝒘𝟑 + …. +𝒙𝒏 𝒘𝒏 ) / ( 𝒘𝟏 + 𝒘𝟐 + 𝒘𝟑 + …. +𝒘𝒏 )

Note:
(i) For same set of data, the weighted mean is generally not equal to the mean, unless
all data have the same weight.
(ii) The weights can be in the form of any non-negative numbers, such as integers,
decimals, or percentages.
(iii) Real life examples of weighted mean: Hang Sang Indexes of Hong Kong Stock
Market, Consumer Price Index (A), Consumer Price Index (B), University Admission
Scores, etc.

Page 21 of 37
Example: The following table lists the marks that Peter got in various subjects in the
mock examination and the weight of each subject.

Subject Chinese English Mathematics Physics Chemistry Biology

Mark 65 75 80 85 82 76
Weight 3 4 3 2 2 2
Find the weighted mean of his examination result, correct to the nearest integer.

Solution
Weighted mean = (65x3+75x4+80x3+85x2+82x2+76x2)/(3+4+3+2+2+2)
=1 221/16
=76 (cor. to the nearest integer)

Example: An English Language examination consists of 3 papers with different

weights. The results of Ken and Peter are shown as follows:

Subject Ken Peter Weight

Paper I 60 80 5
Paper II 70 65 3
Paper III 80 75 2
(a) Find the weighted mean mark of Ken and Peter.
(b) Who performed better?

Solution
(a) The weighted mean mark of Ken = (60x5+70x3+80x2)/(5+3+2) = 67
The weighted mean mark of Peter = (80x5+65x3+75x2)/(5+3+2) =74.5

(b) ∵ Weighted mean mark of Peter > Weighted mean mark of Ken

∴ Peter performed better.

Page 22 of 37
Part 2: Quiz (1)

1. (a) Find the mean of the following set of data.

5p + 2, 10 − 2p, 8+3p, 2p − 1, 7p −4
(b) It is given that the mean of 5 numbers is 67. Find the total sum of these 5 numbers.
(c) The mean of 5 numbers 3, 7, p , 9 and 10 is 6. Find the value of p.
(d) Find the mean of the set of data presented by the following stem-and-leaf diagram.
Stem (10) Leaf (1)

1 2 4 5
2 1 3 5 6
3 3 5 9
(e) The following table shows the ages of some children.
Age 6 7 8 9 10
Number of children 200 180 210 220 180
Find the mean age of the children.

Solution
(a) Mean = [(5p + 2) + (10 − 2p) + (8+3p ) + ( 2p − 1) + (7p −4)] /5
= (15p + 15)/5
= 3p + 3

(b) Total sum of these 5 numbers = 67 x 5

= 335
(c) (3 + 7 + p + 9 + 10 ) / 5 = 6
29 + p = 30
p=1

(d) Mean = (12 + 14 + 15 +21 + 23 +25 +26 +33 + 35 + 39)/10

= 24.3

6  200 + 7 180 + 8  210 + 9  220 + 10 180

(e) Mean age =
200 + 180 + 210 + 220 + 180
=8

Page 23 of 37
2. (i) The mean of a, b and c is 100 and the mean of a, b, c, d and e is 120.
Find the value of d + e .
(ii) The mean weight of 25 apples in a box is 150 g. If 5 apples weighting
a total of 810 g are put into the box, find the mean weight of these 30 apples.

(iii) There are 380 boys and 340 girls in a school. The mean weights of the boys
and the girls are 50 kg and 45 kg respectively. Find the mean weight of all
students in the school. (Give your answers correct to 2 decimal places.)

Solution
(i) a+b+c = 100 x 3 … (1)
a+b+c+d+e = 120 x 5 … (2)

(2) – (1): d+e = 120 x 5 – 100 x 3

= 300

(ii) Total weight of the original 25 apples = 150 x 25 = 3750 g

Mean weight of these 30 apples = (3750 + 810) / (25 + 5) = 152 g

(iii) Mean weight of the students = (380 × 50 + 340 × 45 ) / (380 + 340)

= 47.64 kg (cor. to 2 d.p.)

Page 24 of 37
3. The following table shows the distribution of the weights (in kg) of a group
of students.
Weight (kg) 40 – 44 45 – 49 50 – 54 55 – 59 60 – 64
Frequency (f) 4 14 20 16 6
Find the mean weight of the students.

Solution
Weight (kg) 40 – 44 45 – 49 50 – 54 55 – 59 60 – 64
Class mark (kg) 42 47 52 57 62
Frequency 4 14 20 16 6

42  4 + 47 14 + 52  20 + 57 16 + 62  6
Mean weight =
4 + 14 + 20 + 16 + 6

= 52.5 kg

Page 25 of 37
Part 2: Quiz (2)

1. (a) The table below shows the numbers of family members in 50 families.
Number of family members 2 3 4 5
Frequency 5 17 25 3
Find the median number of family members of the families.

(b) Find the median of the first 10 prime numbers.

Solution
(a) Median number of family members = (4+4)/2
=4

(b) The first 10 prime numbers are: 2, 3, 5, 7, 11, 13, 17, 19, 23, 29.
Median = (11+13)/ 2
= 12

2. Find the modes of the following sets of data.

(a) 12, 23, 14, 80, 79, 18, 22, 19, 37
(b) −8, 15, −3, 29, 44, −8, 12, 15, 25,
(c) 12, 70, 12, 40, 12, 60, 13, 16, 16

Solution
(a) There are no modes in the set of data.
(b) Modes = -8 and 15
(c) Mode = 12

Page 26 of 37
3. (i) Find the median of the following set of data.
p + 8, p − 12, p − 8 , p + 14, p − 2, p + 4, p − 14, p + 18, p + 20, p − 6
(ii) If the median of 4 + a, 20 + a, 22 + a , 6 + a, 24 + a and 2 + a is 30,
find the value of a.
(iii) Find the median of the set of data presented by the following stem-and-leaf diagram.
Stem (10) Leaf (1)
1 0 2 4 5 7
2 3 4 6 7 8 9
3 1 5 8 9
Solution
(i) Arrange the data in ascending order:
p − 14, p − 12, p − 8, p − 6, p − 2, p + 4, p + 8, p + 14, p + 18, p + 20
∴ Median = [ ( p − 2) + ( p + 4) ] / 2
= (2p + 2)/2
= p +1
(ii) Arrange the numbers in ascending order:
2 + a, 4 + a, 6 + a, 20 + a, 22 + a , 24 + a
∵ Median = 30
∴ [(6 + a) + ( 20 + a) ] / 2 = 30
26 + 2a = 60
a = 17

(iii) Number of data = 5 +6 + 4

= 15
∴ Median = 26

Page 27 of 37
Part 2: Quiz (3)

1. The table below shows the marks of 14 students in a Mathematics test.

Boy 80, 70, 85, 75, 90, 65, 92
Girl 73, 68, 82, 74, 81, 62, 86

(a) Find the median mark of the boys in the test

(b) Find the median mark of the girls in the test.
(c) Find the median mark of the 14 students in the test.

Solution
(a) For the boys, arrange the marks in ascending order:
65, 70, 75, 80, 85, 90, 92
Median mark = 80
(b) For the girls, arrange the marks in ascending order:
62, 68, 73, 74, 81, 82, 86
Median mark = 74
(c) Arrange the marks of all the students in ascending order:
62, 65, 68, 70, 73, 74, 75, 80, 81, 82, 85, 86, 90, 92
Median mark = (75 + 80)/2
= 77.5

Page 28 of 37
2.(a) Find the mode of the set of data presented by the following stem-and-leaf diagram.
Stem (10) Leaf (1)
1 2 4 6 9
2 1 5 5 5 5 7
3 1 6 6 6
4 1 3 7

(b) The following table shows the ages of students in a school.

Age 13 14 15 16 17 18
Frequency 155 160 170 170 165 5
Find the mode of the ages of the students.
(c) The following table shows the blood types of 1000 of students in a school.
Blood type O A B AB
Number of
480 380 110 30
students
Find the mode of blood types of the students.

Solution
(a) Mode = 25
(b) Modes of the ages of students in a school = 15 and 16
(c) Mode of blood type is O.

3. The following table shows the shoes sizes of a group of men.

Size 4 5 a 7 8
Frequency 3 10 18 b 5
If the modes of the sizes are 6 and 7, write down the values of a and b.

Solution
a =6
b = 18

Page 29 of 37
4. The table below shows the monthly pocket money of S1 student in a school.
Monthly pocket
200-249 250-299 300-349 350-399 400-449 450-499
money ($)
Number of
7 22 47 20 15 9
students
Find the modal class of the monthly pocket money of the S1 student.
Solution
The modal class of the monthly pocket money of the S1 student is $300 – $349.

Page 30 of 37
Part 2: Quiz (4)

1. Consider the following set of data.

3, 8, 8, 11, 13, 14, 16, 17, 18, 80
(a) Find the mean, the median and the mode of the data.
(b) Which average is the more suitable to reflect the central tendency of this set of
data? Explain your answer.

Solution
(a) Mean = (3 + 8 + 8 + 11 + 13 + 14 + 16 + 17 + 18 + 80) /10 = 18.8
Median = (13 + 14)/ 2 = 13.5
Mode = 8
(b) Since the mean (18.8) is greatly affected by the extreme value (80), it is not suitable
to reflect the central tendency of this set of data.
Since the mode (8) is smaller than most of the datum, it is not suitable to reflect the
central tendency of this set of data.
Therefore, the median (13.5) is more suitable to reflect the central tendency of this
set of data.

2. It is given that the mean, the median and the mode of a set of data are 20, 10 and 30
respectively.
(a) If 2 is subtracted from each datum in the set of data, find the new mean, the new
median and the new mode.
(b) If each datum in the set of data is divided by 5, find the new mean, the new median
and the new mode.

Solution

(a) New mean = 20 – 2 = 18

New median = 10 – 2 = 8
New mode = 30 – 2 = 28
(b) New mean = 20 ÷ 5 = 4
New median = 10 ÷5 = 2
New mode = 30 ÷5 = 6

Page 31 of 37
3. (a) Find the mean, the median and the mode of the data set 13, 15, 15, 15, 18, 19,
28, 29, 40, 49.
(b) Using the results of (a), find the new mean, the new median and the new mode
in each of the following data sets.
(i) 16, 18, 18, 18, 21, 22, 31, 32, 43, 52
(ii) 26, 30, 30, 30, 36, 38, 56, 58, 80, 98

Solution
(a) Mean = (13 + 15 + 15 + 15 + 18 + 19 + 28 + 29 + 40 + 49)/10
= 24.1
Median = (18 + 19)/2
= 18.5
Mode = 15

(b) (i) ∵ 3 has been added to each of the data in (a).

∴ New mean = 24.1 + 3 = 27.1
New median = 18.5 + 3 = 21.5
New mode = 15 + 3 = 18

(ii) ∵ 2 has been multiplied to each of the data in (a).

∴ New mean = 24.1 x 2 = 48.2

New median = 18.5 x 2 = 37
New mode = 15 x 2 = 30

Page 32 of 37
4. The ages of 10 students are shown below:
16, 16, 13, 14, 15, 16, 16, 17, 13, 13
(a) Find the mean, the median and the mode of the ages of the students.
(b) Find the mean, the median and the mode of the ages of the students 3 years ago.

Solution

(a) Mean = (16 + 16 + 13 + 14 + 15 + 16 + 16 + 17+ 13 + 13) / 10

= 14.9
Arrange the ages in ascending order:13, 13, 13, 14, 15, 16, 16, 16, 16, 17
∴Median = (15+16)/2
= 15.5
Mode = 16

(b) Mean age of the students 3 years ago = 14.9 – 3

= 11.9

Median age of the students 3 years ago = 15.5 – 3

= 12.5

Mode age of the students 3 years ago = 16 – 3

= 13

Page 33 of 37
5. The following table shows the results of Tony in Mathematics this term.
1st quiz Mid-term 2nd quiz Final
Examination
Examination
Marks 80 90 85 95
Weight 0.15 0.2 0.15 0.5
Find the weighted mean mark that Tony got in Mathematics this term.
Solution

80  0.15 + 90  0.2 + 85  0.15 + 95  0.5

Weighted mean mark =
0.15 + 0.2 + 0.15 + 0.5

= 90.25

6. The table below shows the marks that Peter and Tony scored in an English
examination and the weight assigned to each paper.
Paper 1 Paper 2 Paper 3 Paper 4
Peter 60 90 65 80
Tony 80 60 85 55
Weight 35% 25% 30% 10%

(a) Find the weighted mean marks of Peter and Tony respectively.
(b) Whose performance is better? Explain your answer.

Solution
60  35% + 90  25% + 65  30% + 80 10%
(a) Weighted mean marks of Peter =
35% + 25% + 30% + 10%

= 71

80  35% + 60  25% + 85  30% + 55 10%

Weighted mean marks of Tony =
35% + 25% + 30% + 10%

= 74
(b) ∵ The weighted mean marks of Tony > The weighted mean marks of Peter

∴ Tony’s performance is better.

Page 34 of 37
7. There are two papers in a Mathematics examination. The result of a student in each
paper and the weight assigned to each paper are shown as follows.
Paper I Paper II
Marks 80 90
Weight p q

If the weighted mean mark of the student in the Mathematics examination is 83,
find p : q.

Solution
∵ Weighted mean mark = 83

80 p + 90q
∴ = 83
p+q
80p + 90q = 83p + 83q
3p = 7q
∴ p:q=7:3

Page 35 of 37
Part 3: Challenging Questions (思考題)
(*=Level 1, **=Level 2, ***=Level 3)

**1. The mean of x1, x2, …, x100 is 80 and the mean of x1, x2, …, x98 is 78.
Find the mean of x99 and x100.

**2. The mean of 11 numbers is 80. If one of the numbers is deleted, the mean
becomes 17. Find the number that is deleted.

**3. It is given that the median of 16, 4, b, b + 3 and 20 is 12, find the value of b.

**4. The table below shows the number of books borrowed from a library by 30
students in one month.
Number of books borrowed 1 2 3 4 5 6
Frequency 2 8 a b 10 1

(a) If the median number of books borrowed is 3.5, find the values of a and b.
(b) If the median number of books borrowed is 3, find all possible pairs of a and b.

**5. It is given that the mean and the median of the data set a, b, c, d and e are 100 and
120 respectively.
(a) Find the mean and the median of the data set a+4, b+4, c+4, d+4, e+4.
(b) Hence, find the mean and the median of the data set -5a-20, -5b-20, -5c-20,
-5d-20, -5e-20.

***6. There are five positive integers a, b, c, d, e arranged in ascending order. Given
that the mean is 6.2, the median is 8 and the mode is 2. Find these five integers.

Page 36 of 37
***7. There are two papers in a Mathematics examination. The table below shows the
marks that Peter and Tony scored in the examination and the weight assigned to each
paper.
Paper I Paper II
Peter 80 92
Tony 85 86
Weight p q

The weighted mean mark of Peter is 83.6.

(a) Find p : q.
(b) Who (Peter or Tony) gets a higher weighted mean mark? Explain your answer.

***8. A company adjusts the selling prices of their drinks as follows:

Product Original selling price ($) New selling price ($)
A 100 120
B 110 130
C 120 147.5
D 200 Out of stock
(a) Find the mean of the original selling of drinks A, B, C and D.
(b) Find the mean of the new selling price of drinks A, B and C.
(c) The company claims that the mean selling price of the drink remains unchanged.
Do you think that the company’s claim is reasonable? Explain your answer.
(d) Find the percentage increase in the mean selling price of drinks A, B and C. (Give
the answer correct to 4 significant figures.)

Page 37 of 37