NNPC FSTP Technicians

Mathematics

Course Code:
 Contents

Statistics
 Module 6: Statistics

• Statistics is the branch of mathematics in

which facts and information are collected,
sorted, displayed and analyzed. Statistics
are used to make decisions and predict
what may happen in the future.
• The word statistics comes from the word
‘state’, largely because it was the job of
the state to keep records and make
decisions based on census results.
 Stages in a Statistical
Investigation
• A statistical investigation normally involves the following
steps:
• Identifying the problem that will be investigated.
Problems can be simple (What is the most popular food
for sale at a school tuckshop?) or more complicated
(Does smoking cause cancer?).
• Collecting the data that you need for making a decision
and solving the problem. Data can be in the forms of a
list, a table or a graph. The data can be collected in
various ways, but observation, interviewing people
(surveys) and using questionaires are the most popular
methods. The number of things observed, or people
surveyed or questioned is called the sample.
• Studying the data, drawing conclusions based on the
data and making decisions.
 Collecting and Organising Data

• Data that have been collected but not organised in any

way are called raw data. Table 1 contains raw data – the
marks obtained by 25 students in a test in the order that
they were gathered.
• An array has certain advantages over raw data. You can
see quite quickly that the marks range from 1 to 10. You
can also see a concentration of values near 7. The array
also roughly reveals the distribution pattern of the marks.
• However, the array is still cumbersome and time-
consuming method of organising data, especially if a very
large sample is involved. Also, once a few types of
information have been obtained, the array is not very
useful. It is far more useful to compress data into a more
manageable, shorter form.
 Frequency Tables

• Raw data can be arranged in a frequency table. A

frequency table shows the number of times
(frequency) each value occurs. A frequency table of
the raw data on fig (a) is represented in the table on
fig (b)
• Fig (a) Table 1
5 5 7 1 6
7 7 5 6 2
5 7 8 7 9
7 10 8 6 3
4 1 8 4 9
• Fig (b)
Mark
1 2 3 4 5 6 7 8 9 10
obtained
Frequency 2 1 1 2 4 3 6 3 2 1
 Tallying

• Tallying is a system of recording and counting

results using diagonal lines grouped in fives.
Each time five is reached, a horizontal line is
drawn through the tally marks to make a group of
five. The next line starts a new group. For
example:
1 I 6 IIII I
4 IIII 10 IIII IIII B
5 IIII 12 IIII IIII
 Graphical Representation

When you work with statistical graphs, you should

remember the following principles:
• The object of any graph is to present the data as
simply and clearly as possible. Lines that criss-cross
each other are confusing, so you should avoid using
them.
• The axes of any graph must be graded and scales
must be chosen carefully. If you exaggerate or
compress the scale of a graph, you may distort the
information shown on the graph.
• The axes must be labelled to show what is marked on
them.
• Every graph should be given a title that tells what is
being shown.
 Pictograms

• A pictogram is a simple way of representing data.

Frequency is indicated by identical pictures
(called symbols or motifs) arranged in rows or
columns. Symbols may be divided into halves or
other fractions to represent parts of a number.
• Pictograms are mainly used in newspapers,
magazines and reports in order to make a striking
display. They are usually aimed at people who
are unskilled in statistics or who have limited
interest in the information shown, and are more
suitable for comparisons than measurements.
 Constructing Pictograms

• Follow these steps to construct a pictogram:

• Round off the figures if necessary (2 significant
figures are normally acceptable).
• Decide on a convenient unit for the symbols;
these are normally whole numbers such as
hundreds, tens or millions.
• Select a symbol for each unit. Make sure it can
be drawn easily.
• Provide a key to explain what the symbols
represent.
• Give the pictogram a title.
 Bar Graphs

• In bar charts or bar graphs, data are represented

in a series of bars that are equally wide. The
width itself is not significant, but all the bars
should be the same width. Sometimes the bars
are just thick lines.
• Bars can touch each other or be separated by
gaps of equal width. The height of the bars
represents the magnitude or frequency of the
figures. Bars may be horizontal or vertical.
• Bar charts are particularly useful for showing
more than one set of facts. This makes them
useful for comparing data.
 Constructing Bar Graphs

• Follow these steps to construct a bar graph:

• Organise the data in a table.
• Round off the numbers if necessary (2 places are usually
sufficient).
• Decide whether the bars will be vertical or horizontal.
• Draw the axes a convenient length.
• Choose an appropriate scale for the numerical axis
(horizontal or vertical). Divide the axis equally according to
the scale you have chosen and label the divisions.
• Decide how wide the bars will be and how much space, if
any, you will leave between them.
• Construct the bars using the appropriate numerical values
on the scale.
• Label the axes and give the graph a proper title.
 Example

• The marks obtained by 50 students in a class test

are given below. Make a frequency table for the
given marks. Draw a bar graph to represent the
data.
Raw Data
10 3 6 4 7
7 4 5 6 9
4 8 6 7 5
5 6 7 5 4
6 5 6 9 1
8 2 3 4 1
7 5 4 6 7
6 4 5 6 8
7 5 6 1 6
5 4 6 7 7
 Solution

Marks Tally Frequency

1 III 3
2 I 1
3 II 2
4 IIII II 7
5 IIII IIII 10
6 IIII IIII II 12
7 IIII IIII 9
8 III 3
9 II 2
10 I 1
 Exercise

• A survey recorded the number of people living in each of 40

houses. The numbers were as follows:
3 4 2 4 3 2 2 5 4 3
4 1 2 6 3 5 5 2 4 1
4 3 4 2 4 4 6 2 4 3
2 5 4 5 6 4 2 3 2 4

(a) Complete the following table.

Number of Tally Number of
people marks houses
1
2
3
4
5
6
 Pie Charts

• A pie chart is a circle graph in which the

angles of the sectors represent the
frequency. When sectors are nearly the
same size, it is difficult to compare them.
In such cases, the measurements are
usually given on the graph.
 Constructing Pie Charts

Follow the steps to draw a pie chart:

• Add all the frequencies (items) and write each
frequency as a fraction of all the frequencies.
• Change each fraction into a number of degrees by
multiplying by 360°.°. ((There are 360°° in a circle.) the
degrees tell you how big the angles of each sector in
the pie chart will be.
• Tabulate the angles in ascending or descending
order.
• Draw a circle of convenient size. Then draw a radius
as a starting point.
• Use a protractor to construct the angles at the centre
corresponding to each sector.
 Examples
• The table below shows how a student spends her day.
Activity School Sleeping Homework Eating Other
No. of 8 8 3 1 4
hours

Show this on a pie chart.

Solution
• Start by working out the fractions.
Total no. of hours = 24
School: , Sleeping: , Homework: , Eating: , Other:

• Change each fraction to degrees.

School: x 360° = 120° Sleeping: x 360° = 120°

Homework: x 360° = 45° Eating: x 360° = 15°

Other: x 360° = 60°

 Examples (contd.)

• Tabulate the angles and use the step-by-step method

below to draw the pie chart.
• Draw a radius as a starting point. Then draw the first 120°
sector.
• Draw the next 120°° sector and the other sectors.
• Label the graph and give it a title.
Activity School Sleeping Other Homework Eating
Angle 120° 120° 60° 45° 15°
Time spent on activities in one day

School
Sleeping
Other
Homework
Eating
 Exercise
1. The table below shows the number of students in a
university and their faculty. Draw a pie chart to
illustrate this information.
Faculty Students
Science 495
Arts 375
Medicine 108
Engineering 54
Law 48

2. The table below shows how an income of ₦400 was

spent. Show these data on a pie chart.
Items Food Rent Clothing Transport Savings
Amount ₦120 ₦80 ₦40 ₦110 ₦50
 Averages – Mean, Median and Mode

Different kinds of averages are used in statistics,

they are called the mean, median and mode. Each
one has a specific purpose and is used differently.

The Mean
The mean is the most common type of average. It is
the number obtained by dividing the sum of all items
by the number of items.
Mean =

The mean of a set of data can also be obtained.

 Example

• Find the mean of 8, 9, 7, 6, 8 and 10.

Sum of items = 8 + 9 + 7 + 6 + 8 + 10 = 48
Number of items = 6
Mean = =8

The mean can also be represented as a formula:

• x is read ‘x bar’ mean

• x1, x2, …, xn are the items
• N represents the number of items
 Examples (contd.)
• Calculate the mean for the following frequency distribution.
Test Marks 1 2 3 4 5 6 7 8 9 10
Frequency 2 3 4 10 5 3 2 1 0 1

• Redraw the table with another row. Label the test marks x,
the frequency f and the last row fx. Add a column at the end
for totals
• Calculate fx and fill in the figures in the last row.
• Calculate the total for row (f and fx) and fill it in.

Test marks (x) 1 2 3 4 5 6 7 8 9 10 Total

Frequency (fx) 2 3 4 10 5 3 2 1 0 1 31
Fx 2 6 12 40 25 18 14 8 0 10 135
• You can work out the mean:
Mean = = 4.35
 The Median

In order to find the median of a set of data, these

must be arranged in ascending or descending
order. The median is the central or middle figure.
• For an odd number of items, the median is the
value of the item that is in the middle.
• For an even number f items, the median is the
mean value of the two middle items.
 Examples

1. Find the median of the following scores:

20 70 50 30 35 45 75 15 90
Solution
Arrange the data in ascending or descending order.
Ascending order:
15 20 30 35 45 50 70 75 90
There are 9 scores, so the 5th is the middle once.
Thus, the median is 45.

2. Find the median of: 6 5 3 8 4 2

Solution
Arrange in order: 2 3 4 5 6 8
There is an even number, so the median is the mean
value of the 3rd and 4th values.
 The Median of a Frequency
Distribution
The example below shows how the median can be
found from a frequency table.
Example
The distribution of marks obtained by the students
in a class is shown in the table below.

Marks obtained 0 1 2 3 4 5 6 7 8 9 10
Number of
1 0 3 2 2 4 3 4 6 3 2
students

Find the median of this distribution.

 Solution

• The total number of students = 1 + 0 + 3 + 2 + 2 + 4 + 6 + 3 +

2 = 30
= 15.5

• The median is the mean of the 15th and 16th marks when the
marks are placed in ascending (or descending) order.
• Add up the frequencies (number of students) in the
table, starting at the left-hand end, until you reach the 15th and
16th students.
1 + 0 + 3 + 2 = 6 so the 6th student obtained 3 marks
6 + 2 = 8 so the 8th student obtained 4 marks
8 + 4 = 12 so the 12th student obtained 5 marks
12 + 3 = 15 so the 15th student obtained 6 marks
The 16th student is the next group (of 4) and so obtained 7 marks.
 The Mode

• The mode of a set of data is the value with

the highest frequency. If there are more
than two values that appear most
frequently, then there is no mode – such a
distribution is non-modal.
• The mode requires no calculation, only
counting.
 Examples

1. Find the mode for the following distribution:

70 80 50 95 80 73 90 85
Solution
80 appears twice, so it is the mode.

2. Find the mode of the given distribution

Marks 0 1 2 3 4 5 6 7 8 9 10

Students 2 1 1 2 6 10 7 6 3 1 1

Solution
The highest frequency is 10. However, remember
that the mode refers to the actual data, so the modal
value is 5
 Exercises
1. Construct a frequency table for the following data and
calculate the mean.
3 4 5 1 2 8 9 6 5 3 2 1 6 4 7 8 1
1 5 5 2 3 4 5 7 8 3 4 2 5 1 9 4 5
6 7 8 9 2 1 5 4 3 4 5 6 1 4 4 8
2. Find the median value of:
a) 100, 75, 85, 95, 43, 99, 70, 60
3. Find the mode of each of the following sets of numbers:
a) 4, 5, 5,1, 2, 9, 5, 6, 4, 5, 7, 5, 5
4. A man kept count of the numbers of letters he received each
day over a period of 60 days. The results are shown in the
table below.
Numbers of letters per day 0 1 2 3 4 5
Frequency 28 21 6 3 1 1
For this distribution, find:
a) the mode b) the median c) the mean.
 Grouped and Continuous Data

Finding the mean of grouped data

In order to calculate the mean of grouped data, you
need to:
• Find the mid-point of each interval (x)
• Multiply the frequency of each interval by its mid-
point (fx).
• Find the sum of all the products fx
• Find the sum of all the frequencies
• Divide the sum of all the products fx by the sum
of the frequencies.
 Examples

1. The table below shows the lengths of 50 pieces of wire

used in a physics laboratory. Lengths have been
measured to the nearest centimetre. Find the mean.

Length 26 – 30 31 – 35 36 – 40 41 – 45 46 – 50
Frequency (f) 4 10 12 18 6

Solution
Find the mid-points of each interval:
Length 26 – 30 31 – 35 36 – 40 41 – 45 46 – 50
Frequency (f) 4 10 12 18 6
Interval 25.5 – 30.5 30.5 – 35.5 35.5 – 40.5 40.5 – 45.5 45.5 – 50.5
Mid-point (x) 28 33 38 43 48
 Solution (contd.)

• Multiply f by x
Length 26 – 30 31 – 35 36 – 40 41 – 45 46 – 50

Frequency (f) 4 10 12 18 6

Mid-point (x) 28 33 38 43 48

fx 28 x 4 33 x 10 38 x 12 43 x 18 48 x 6
= 112 = 330 = 456 = 774 = 288

• Find the totals:

Sum of fx = 1960
Sum of f = 50
The mean = (1960 ÷ 50)cm = 39.2
 Histogram

Histograms are like vertical bar graphs of

grouped data. There are no gaps between
the bars. The area of the bars gives the
number of items in the class interval. If all
the class intervals are the same, then the
bars will be the same width, and frequencies
can be represented by the heights of the
bars.
 Example

1. Draw a histogram to illustrate the following frequency

table. The measurements were made to the nearest unit.
Class interval 10 – 24 25 – 39 40 – 54 55 – 69 70 – 84 85 – 100
Frequency 1 4 11 5 3 3

Solution
The class boundaries are:
9.5 24.5 39.5 54.5 69.5 84.5 99.5

The class are:

15 15 15 15 15 15

Area of rectangle = class width x height of rectangle.

As the class width is 15 for each interval, area of rectangle =
15 x height of rectangle. So, are x height of rectangle.
If you make the height of each rectangle the same as the
frequency.
 Example (contd.)

So you can draw the frequencies along the vertical axis and
the class interval along the horizontal axis
11

10

8
Frequency

0
9.5 24.5 39.5 54.5 69.5 84.5 99.5

Class intervals
 The Mode of a Grouped
Frequency Distribution

It should be noted that you cannot find the

mode of grouped data but rather only the
modal class (or classes). The modal class is
the class interval that has the largest
frequency. However, the way in which the
class intervals are chosen affects which
class interval forms the modal class.
 Example

• Find the modal class of the frequency distribution below:

Marks Frequency

6 – 15 2
16 – 25 7
26 – 35 9
36 – 45 3
46 – 55 4
56 – 65 2
66 – 75 1

Solution
The highest frequency is 9.
The interval against this is 26 – 35. So the modal class is 26 – 35.
 Example (contd.)

The Histogram

10

Frequency 8

0
5.5 15.5 25.5 35.5 45.5 55.5 65.5 75.5

Marks
 Exercise

• The height of 25 plants were measured to the

nearest centimetre. The results are summarised
in the table below:
Number of
Height in cm
plants
5 – 14 4
15 – 19 8
20 – 24 7
25 – 39 6

Find the modal class and draw a histogram to

illustrate the distribution.
 Dispersion and Cumulative
Frequency
Dispersion
• The average (mean, median or mode) gives a general
idea of the size of the data, but two sets of numbers
can have the same mean while being very different in
other ways.
• The other main statistic we need to find is a measure of
dispersion or spread. There are several ways of
measuring dispersion.
Range
• The range is the easiest measure of dispersion to
calculate. It is defined as the difference between the
highest value and the lowest value. The range is a
crude measure of dispersion since it makes no use of
the intermediate values and it can be distorted by one
or two extreme values.
 Inter-quartile Range
• This is a measure of the middle half of the data, so it is
more representative. A distribution is divided into four
subgroups by three quartiles.
• The first or lower quartile (Q1) is the point below which 25%
of the items lie and above which 75% of the items lie.
• The second quartile (Q2) is the point below which 50% of
the items lie and above which 50% of the items lie. You will
realise that the second quartile is the same as the median.
• The third or upper quartile (Q3) is the point below which
75% of the items lie and above which 25% of the items lie.
• If there are n values, in ascending order, then the lower
quartile Q1 is the th value, and the upper quartile Q3
is the th value.
• The inter-quartile range = Q3 – Q1.
 Percentiles

• The median and quartiles divide a distribution into

four parts. For a large mass of data, these may not
give sufficient information. In such cases, two other
sets of measures are useful. They are deciles and
percentiles.
• Deciles divide the distribution into 10 equal parts.
• Percentiles divide the data into 100 equal parts.

For example, the 10th percentile P10 = (n + 1)th

value.

The 90th percentile P10 = (n + 1)th value.

 Example
1. A student’s marks in ten subjects in two sets of tests are given
below.
Test 1: 20 22 28 19 20 24 23 20 24 20
Test 2: 13 15 36 11 18 30 23 8 32 34

Find, for each set of tests:

(a) the range (b) the median (c) the mean
Solution
a) Range
Test 1: 28 – 19 = 9
Test 2: 36 – 8 = 28
b) Median
Test 1: =1

Test 2: = 20.5
c) Mean
Test 1: 220 ÷ 10 = 22
Test 2: 220 ÷ 10 = 22
 Cumulative Frequency Table

The word ‘cumulative’ is related to the word

‘accumulate’, which means to ‘pile up’. In
other words, the cumulative frequency
column shows the running total of the class
frequencies. A cumulative frequency table
gives the total up to each class boundary.
 Example

• This will be clear from the table below, which

gives the marks obtained by 100 candidates in an
examination.
• The last number of the cumulative frequency
column gives the total number of items or the
sum of the frequencies. The cumulative
frequency column shows us that 2 candidates
scored 9 or less, 6 candidates scored 19 or less,
and so on. The successive entries are obtained
by adding the next figure in the frequency column
to the previous total figure. This is what is implied
by the word ‘cumulative’.
 Example (contd.)

Cumulative
Score Frequency
frequency

0–9 2 2
10 – 19 4 6
20 – 29 8 14
30 – 39 10 24
40 – 49 12 36
50 – 59 25 61
60 – 69 22 83
70 – 79 8 91
80 – 89 6 97
90 – 99 3 100

The cumulative column will be obtained thus,

 Solution
Frequency Cumulative frequency
2 2
4 2+4=6
8 2 + 4 + 8 = 14
10 2 + 4 + 8 + 10 = 24
12 2 + 4 + 8 + 10 + 12 = 36
25 2 + 4 + 8 + 10 + 12 + 25 = 61
22 2 + 4 + 8 + 10 + 12 + 25 + 22 = 83
8 2 + 4 + 8 + 10 + 12 + 25 + 22 + 8 = 91
6 2 + 4 + 8 + 10 + 12 + 25 + 22 + 8 + 6 = 97
3 2 + 4 + 8 + 10 + 12 + 25 + 22 + 8 + 6 + 3 = 100

• It should be noted that the last entry will be

equal to the sum of the entire class entries.
 Cumulative Frequency Curve

• The curve obtained by plotting cumulative

frequencies against the upper boundaries of the
classes is called a cumulative frequency curve.
(The curve’s sometimes called an ‘ogive’ from a
curve used in architecture.)
• If the points are joined by straight lines, the graph
is called a cumulative frequency polygon.
 Exercise

1. The heights of 25 plants were measured to the

nearest centimetre. The results are summarised
in the table.
Height in cm 6 – 15 16 – 20 21 – 25 26 – 40
Number of plants 3 7 10 5

a) Draw up a cumulative frequency table for this

distribution.
b) In which interval does the median plant
height lie?
c) Estimate, to the nearest centimetre, the
median plant height.
END