0% found this document useful (0 votes)
18 views

Presentation of Statistical Data

ST

Uploaded by

ancestorsage
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
18 views

Presentation of Statistical Data

ST

Uploaded by

ancestorsage
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 25

Presentation of Statistical Data

Statistical data are organised and classified into groups before they are presented for
analysis. Four important bases of classification are:
(a) Qualitative – By type or quality of items under consideration;
(b) Quantitative – By range specified in quantities;
(c) Chronological – Time series – Monthly or Yearly: An analysis of time series
involving a consideration of trend, cyclical, periodic and irregular movements;
and

1
d) Geographical – By location.
The classified data are then presented in one of the following three methods:

(a) Text presentation; (b) Tabular presentation; and (c) Diagrammatic presentation:

Text Presentation
This is a procedure by which texts and figures are combined. It is usually a report
in which much emphasis is placed on the figures being discussed.
For instance, a text presentation can be presented as follows:
The populations of science and management students are 3,000 and 5,000
respectively for year 2006 in a Polytechnic in Ghana.

Tabular presentation
A table is more detailed than the information in the text presentation. It is brief and self-
explanatory. A number of tables dealt with in statistical analysis are general reference
table, summary table, Time series table, frequency table.
Tables may be simple or complex. A simple table relates a single set of items such
as the dependent variable against another single set of items s u c h a s the
independent variable. A complex table, on the other hand, has a number of items
presented and often shows sub-divisions.
Essential features of a table are:
- A title to give adequate information about it;
- Heading for identification of the rows and columns;
- Source i.e. the origin of the figures; and
- Footnote to give some detailed information on some figures in the table.
Example 1.1 (A typical example of simple table)
Classification of two hundred Polytechnic students on departmental basis
Department No of Students
Accountancy 60

Business Administration 50

Marketing 40

Banking / Finance 50
Total 200
2
Example 1.2 (A Typical Example of Complex Table)
Departmental classification of 200 University students on the basis of gender
Department No of Students
Total
Male Female
Accountancy 40 20 60
Business Administration 36 14 50
Marketing 30 10 40
Banking / Finance 24 26 50
Total 130 70 200

Formulation of Frequency Table


A frequency table is a table showing the number of times a value (figure) or group of
value (figure) has occurred in a given set of data.
It can be ungrouped or grouped.

- Ungrouped frequency table


This shows the figure (value) in one column and the number of times (frequency)
it has occurred in the given data.

Example 1.3

The marks scored by 20 candidates out of 10 marks in a quiz


competition were as follows:

6, 7, 4, 5, 6, 4, 5, 8, 7, 6,
9, 8, 4, 6, 5, 7, 6, 5, 8, 7,
Obtain the frequency distribution for the data solution

Solution
No. Of candidates
Mark (frequency)
4 3
5 4
6 5
7 4
8 3
9 1

3
- Grouped table:
Guidelines for constructing a grouped frequency table
viii. The number of class intervals (or classes) should not be too few or too many
(say 5 to 8 classes);
ix. The class width should be 5 or multiple of 5 to allow for easy manipulation;
x. The classes should generally be of the same width except where there are
extreme values when the opening and closing classes may be wider to take
care of the extreme values;
xi. The classes must be such that each observation will have a distinct class.
Classes must not be of the types 5 – 10, 10 – 15, etc. These will create a
problem of which class 10 belongs;
xii. Class intervals could be of the type 1 – 5, 6 – 10, 11 – 20, 21 – 20, etc.’, 10
but less than 20, 20 but less than 30, etc. The size of observations combined
with (i) above could determine the width of the classes;
xiii. Open-ended classes (e.g. less than 20, 10 and above) are assumed to have
the same width as adjacent classes.

Usually, Tally Method is used to construct a frequency table especially when


there are many observations (figures).
A tally is a stroke (│) drawn for each occurrence of an observation. The fifth
stroke (tally) is drawn across the first four strokes (| | | |); this allows for easy
counting.
The great advantage of the tally method is that you go through the data only
once. It removes the confusion which may arise when each observation is
counted throughout the data.

Example 1.4
The daily sales figure (N’000) of a supermarket for 40 days were as follows:
12, 33, 23, 48, 56, 18, 22, 55, 57, 35,
45, 28, 36, 44, 17, 39, 58, 25, 31, 48,
26, 32, 45, 24, 35, 47, 56, 33, 27, 31,
34, 19, 21, 35, 41, 32, 45, 37, 29, 49,

4
You are required to:
Use class intervals of 11 – 20; 21 – 30; etc., to construct a frequency table for the
sales.

Solution
Class Intervals Tally Frequency
11 – 20 |||| 5
21 – 30 |||| |||| 9
31 – 40 |||| |||| |||| 14
41 – 50 |||| || 7
51 – 60 |||| 5

NOTE:
(a) Class Limits
The first number in a class is called the lower class limit while the
second number is the upper class limit.

e.g. lower class limit of the 3rd class is 31 while its upper class limit is 40

(b) Class Boundaries


i. The lower class boundary of a class is the sum (addition) of the
upper class limit of the preceding class and its lower limit divided by
2.
e.g. the lower class boundary of the 2nd class is:
[20 (upper class limit of 1st class) + 21 (its lower class limit)] ÷ 2
41
  20.5
2
ii. The upper class boundary of a class is the sum of its upper limit and
the lower limit of the succeeding class divided by 2
e.g. the upper class boundary of the 2nd class is:
[30 (its upper limit) + 31 (lower limit of 3rd class)] ÷ 2
30  31
  30.5
2
Consequently, the lower class boundary of a class is the upper class boundary of the
class preceding it. Class boundaries are used to draw histograms and ogives.

5
(c) Class Size (Width)
The width of a class is the difference between its boundaries.
e.g. The width of the 2nd class is 30.5 – 20.5 = 10
The lower boundary for 1st class and upper boundary for last class
are obtained by logic

(d) Class Mid-point


The mid-point of a class is the sum of its limits divided by 2.
41  50
e.g. the mid-point of the 4th class is  45.5
2
Note that the mid-point of a class is the sum of the mid –point of the
preceding class and the class width.
Class marks are used to represent class intervals in the calculation of
statistical measures. They are also used in drawing the frequency polygon

Cumulative Frequency Table


A cumulative frequency table is a table showing the sum of frequencies of all classes
before a particular class and the frequency of that class.

Example 1.5
Obtain the cumulative frequency table for the frequency table below:
Class Intervals Frequency
11 – 20 5
21 – 30 9
31 – 40 14
41 – 50 7
51 – 60 5

Solution
Class Intervals Frequency Cumulative
frequency
11 – 20 5 5
21 – 30 9 5 + 9 = 14
31 – 40 14 14 + 14 = 28
41 – 50 7 28 + 7 = 35
51 – 60 5 35 + 5 = 40

6
Diagrammatic Presentation:
Diagrams are used to reflect the relationship, trends and comparisons among variables
presented on a table. The diagrams are in form of charts and graphs.

(a) Charts
i. Bar charts
A bar chart is a chart where rectangular bars represent the information. The
bars must be of equal width with heights or lengths proportional to the values
which they represent. The bars can be plotted vertically (usually or
horizontally and can take various forms as discussed below.
 Simple bar chart;
 component bar chart;
 Multiple bar charts.
 Simple Bar Chart
This consists of a series of bars with the same width while the height of each
bar indicates the size of the value it represents.

7
Example 1.6
Draw simple bar chart for the table below:
Department No of Students

Accountancy 60

Business Administration 50

Marketing 40

Banking / Finance 50
Total 200

70
60
50
40 Departments Key
Students

30 Accountancy A
No of

20
Business Admin BA
10
0 Marketing M
A BA M BF Banking/Finance B/F
Departments

 Multiple Bar Chart

This shows each group as separate bars beside each other.

Example 1.7
Draw Multiple bar chart for the following table:
Department No of Students
Male Female
Accountancy 40 20
Business Administration 36 14
Marketing 30 10
Banking / Finance 24 26

8
45
M
40
F
35
30
25

Students
20

No of
15
10
5
0
A BA M B/F
Department

 Component Bar Chart


This is similar to simple bar chart. The heights of each bar are divided
into component parts.

Example 1.8
Draw component bar chart for the following table

Department No of Students
TOTAL
Male Female
Accountancy 40 20 60
Business Administration 36 14 50
Marketing 30 10 40
Banking / Finance 24 26 50

9
70

60

50

No of Students
40

30

20

10
Female

0
Acc. Bus. Adm Marketing B/Finance
Department

ii. Pie Chart


A pie chart is a circular chart which is divided into sectors. Each sectorial
angle represents the parts in degrees.

Example 1.10
Draw Pie chart for the table. Classification of two hundred polytechnic
students on departmental basis
Department No of Students
Accountancy 60
Business Administration 50
Marketing 40
Banking / Finance 50

Solution
Calculation of angles
Total no of students is 200 and the sum of angles in a circle is 360

10
11
 For Accountancy, the corresponding angle 60 360
   108
200 1
For Business Administration, the corresponding angle 50 360
 200  1  90

For Marketing, the corresponding angle 40 360


 200  1  72

For Banking/Finance, the corresponding angle 50 360


 200  1  90

Check: 108  90  72  90  360

12
Pie chart

90
108

Accountacy
Business
Admin
Marketing
72

90

(b) Graphs
A graph shows relationship between variables concerned by means of a curve or
a straight line. A graph will, for example, show the relationship between output
and cost, or the amount of sales to the time the sales were made.
Typical graphs used in business are the histogram, frequency polygon and
cumulative frequency curve (ogive).

(i) Histogram
A histogram consists of rectangles drawn to represent a group
frequency distribution. This is similar to a bar chart but
- the rectangles must touch each other (continuous); and
- The frequency of a class is represented by the area of the
corresponding rectangle (not its height as in the bar chart).

13
If the class sizes are not equal, the frequency of a class with different
class size must be adjusted as follows:
- Choose the size common to most of the classes

Adjust the other frequency as follows:


- Common size divided by the size multiplied by the frequency.
e.g. if the size is double that of the common size, its frequency
is divided by 2

Example 1.11
Draw the histogram for the frequency table of sales figures given below:

Class interval Frequency


(Sales) (No. of days)
11 – 20 5
21 – 30 9
31 – 40 14
41 – 50 7
51 – 60 5

Solution
Since the rectangles in a histogram must be continuous (touch each other), the
class intervals are written using the class boundaries thus:

Class interval Frequency


(Sales) (No. of days)
10.5 – 20.5 5
20.5 – 30.5 9
30.5 – 40.5 14
40.5 – 50.5 7
50.5 – 60.5 5

The histogram can be used to estimate the modal value.

14
Histogram

15

10
Frequency

ᶬ 10.5 20.5 30.5 40.550.5 60.5


Sales
ᶬ indicates that the horizontal scale does not start from 0 (zero)

(ii) Frequency Polygon


A frequency polygon is the graph of frequencies against class marks.
If the histogram to a frequency table has been drawn, the frequency
polygon is obtained by joining the mid-points of the top of the rectangles.
The polygon is closed up by joining to the class mark of the class before
the first and after the last class intervals with zero frequencies.

Example 1.12

Draw the frequency polygon for the table below:

Class interval Frequency


(Sales) (No. of
days)
11 – 20 5
21 – 30 9
31 – 40 14
41 – 50 7
15
51 – 60 5

16
Solution
Class interval Class Mark Frequency
(Sales) (No. of days)
1 – 10 5.5 0
11 – 20 15.5 5
21 – 30 25.5 9
31 – 40 35.5 14
41 – 50 45.5 7
51 – 60 55.5 5
61 – 70 65.5 0

Frequency Polygon

16

14

12

10
Frequency

0
5.5 15.5 25.5 35.5 45.5 55.5 65.5

Sales

The points are joined with a straight edge but when it is smoothened
out it becomes a frequency curve which shows the shape of the
frequency distribution.

(iii) Ogive
An ogive is a graph of cumulative frequencies against class boundaries.
It is also referred to as the cumulative frequency curve. It could be ‘less
than’ type or ‘greater than’ type.
17
Example 1.13
Draw the ogive for the frequency table below
class interval Frequency
11 – 20 5
21 – 30 9
31 – 40 14
41 – 50 7
51 – 60 5

Solution

Less than Cumulative


(or equal to) frequency
10.5 0
20.5 5
30.5 14
40.5 28
50.5 35
60.5 40

45

40

35

30

25

20

15

10

0
10.5 20.5 30.5 40.5 50.5 60.5

The points are to be jointed with free hand

NOTE:

‘Or equal to’ is understood and usually hidden so only ‘less than’
is used.
18

In the frequency table, no value is less than 10.5 (the upper class
boundary of the class before the first class), hence, the cumulative
frequency of zero (0) and no value is greater than 60.5 (the upper
class boundary of the last class), hence, the cumulative frequency
of 40 which is the total frequency.
The ogive can be used to estimate median, quartiles, deciles
and the percentiles.

REMARK

In the construction of ogive (cumulative frequency curve) in
example 1.13, the approach used in drawing the ogive is the ‘less
than’ type. However, there is another approach tagged ‘more than’.
The major differences between the two approaches are as follows:
(i)
Cumulating the frequencies in ‘less than’ and ‘more than’
starts respectively from top and bottom frequencies; and
(ii)
The cumulative figures are attached to upper class boundaries
for ‘less than’ while they are attached to lower class
boundaries for ‘more than’.
Let us consider the following example for the ‘more than’ case:

Example 1.14
By using example 1.13 data, construct a ‘More than’ ogive
The cumulative table for ‘more than’ is as follows:
class boundary frequency cumulative
frequency
More than 10.5 5 40
More than 20.5 9 35
More than 30.5 14 26
More than 40.5 7 12
More than 50.5 5 05
40

19
Solution

45

40

35

30

25

20

15

10

10.5 20.5 30.5 40.5 50.5 60.5

Example 1.15
In a class of accounting students, the students were tested on
‘Quantitative Analysis’. The following table depicts the scores of these
students in a tabular from:

Marks in interval Number of Students


0 – 10 5
10 – 20 10
20 – 30 15
30 – 40 20
40 – 50 25
50 – 60 10
60 – 70 5
70 – 80 4
80 – 90 3
90 – 100 3
Draw the ogive for the table.

20
Solution
More than
Class boundary Frequency Cumulative frequency
More than 0 5 100
More than 10 10 95
More than 20 15 85
More than 30 20 70
More than 40 25 50
More than 50 10 25
More than 60 5 15
More than 70 4 10
More than 80 3 06
More than 90 3 03
100

Less than
Class boundary Frequency Cumulative frequency
Less than 10 5 05
Less than 20 10 15
Less than 30 15 30
Less than 40 20 50
Less than 50 25 75
Less than 60 10 85
Less than 70 5 90
Less than 80 4 94
Less than 90 3 97
Less than 100 3 100
100

21
Comment on the Ogives
The above graphs are the ogives of ‘less than ‘and ‘more than ‘on the same axes.
From the drawn ogives, it could be seen that the two ogives intercept at the class
boundary of 40 at cumulative frequency 50. The intersection implies that the median
value is 40

1.5 The use of statistical application packages for data presentation.


In the advent of computer, there are lots of computer applications available to make

22
operations like accounting process, statistical process etc. easy to comprehend.
Statistical Application Package is one of such computer applications. There are many
statistical application packages that have been developed for different purposes such as
data presentation and analysis. But the two commonly used one are Microsoft Excel and
SPSS.
However, a good knowledge of statistics and computer know-how are required to
interpret and understand these packages.
The statistical packages make use of the speed, efficiency and accuracy of the computer
to analysis data effectively.
We will now explain the use of the two packages mentioned above for data presentation.
(a) MICROSOFT EXCEL
This is a spreadsheet developed by Microsoft for windows android, MAC OS
and IOS, which can sometimes be called; “EXCEL” (short form). It has a lot of
features which include graphic tools, pivot tables, calculations and visual basic
(programming language) for applications.
Excel forms part of installed Microsoft office in your personal computer or
laptop. It has a set of in-built functions that are used to answer appropriate
engineering, statistical and financial questions. It is used to perform variety of
computations which include a data analysis tool pack and collection of statistical
functions which can display data in different types of table, charts and graphic.
The steps below explain how excel application can be used for data presentation:
(i) Clock on all program options from the start menu;
(ii) Search for Microsoft office (which always comes with year i.e. for
example Microsoft office 2020) from the sub menu and then click on it;
(iii) From the Microsoft office sub menu, search for Microsoft excel (which
also comes with a particular year i.e. Microsoft excel 2020) from the sub
menu and then click on it;
(iv) The Microsoft excel application chosen would be launched and a new
spreadsheet (which contains a lot of cells i.e. intersection between rows
& Colum);
(v) Data to be analyzed are then entered into the different cells along the
columns;

23
(vi) Highlight the part of data entered that are to be worked on;
(vii) Go to the menu, select the chart wizard icon and click on it or click on
insert from the menu and then click on chart and select and click on the
desired type of chart (i.e. pie chart or bar chart). Also, for further
analysis, select data from the menu bar and locate the data analysis and
search for the desired statistical tools; and
(viii) The result/output is displayed and it is then saved for use.
NOTE:
In the Microsoft excel menu, the help or tutorial menu can be used as a guide to
carry out the appropriate data presentation correctly.
(b) SPSS
The acronym SPSS which stands for “Statistical Package for the Social
Sciences” is a set of programs for presentation, manipulation and analysis of
different data sets. The SPSS was originally developed by SPSS INC. which has
now been acquired by international business machine (IBM) and it is now known
as IBM SPSS statistics. The SPSS was originally developed for researchers in
the field of social sciences like & psychology, sociology etc., but since the
acquisition by IBM, it has been expanded into different fields. The SPSS
software has been developed in a customised manner to allow one to enter the
needed exact data like numbers (quantitative) and variables (quantitative). It has
a user interface like that of Microsoft excel i.e. spreadsheet set up. Unlike the
Microsoft excel that comes with the Microsoft office, the SPSS software has to
be installed on your personal computer or laptop (the free trial version can be
downloaded from the IBM SPSS site or it can be from appropriate software site).
SPSS software has four different windows, namely: data editor window, output
window, syntax window and script window but data editor and output window
are of major concern in the data analysis environment. The data editor window
consists of two view, namely: the data view and the variable view, while the data
view displays the actual data entered and variables created, the variable view
contains the definition label of each variable in the data set. On the other hand,
the output window displays result of the analysis for interpretation.
The steps below explain how SPSS can be used for data:

24
(i) Click on all programs option from the start menu;
(ii) Search for the SPSS software installed i.e. SPSS 22.0 and click on it:
(iii) SPSS data editor window will be launched;
(iv) A dialog box will appear asking if one wants to” open an existing data
file” or to “enter a new data set” where one has to select one, most of the
time, “enter a new data set” is selected;
(v) The data editor window will be launched where one has to click on the
variable view to define and label the data set and then click on the data
view to input/enter the data based on the definition and labelling under
the variable view;
(vi) From the SPSS menu at the top, search for analyze and click on it and
select the desire statistical tool to be performed i.e. frequency
distribution, chart and graphs for the set of data selected as well and click
ok; and
(vii) The output window will be launched showing the result output of data
the analysis presentation and it can then be saved for the SPSS menu.
NOTE:
In the SPSS menu, the help or tutorial menu can be used as a guide to
carry out the appropriate data presentation correctly.

25

You might also like