DATA VISUALIZATION

Dr. Furqan Awan

Dept of Epidemiology and Public health
TERMINOLOGIES
DATA PRESENTATION

Data
Visualization

Diagrams/
Tables Graphs
TABULATION
TABULATION- ADVANTAGE

Simplify - Remove the complexities of raw data

Bird Eye View - Summarize huge data in the concise form

Comparison - Helpful in comparing data

Identify mistakes - Any big mistake or error in data can easily be identified
RULES OF TABLE FORMATION:
IV VS DV
There are 90 students in a classroom
We want to study
Marks percentage is same among all students?
OR
Marks percentage is varying among all students?

Which one is IV and DV?

IV VS DV
Marks % age No. of Students
There are 90 students in a classroom 50 – 60 20
We want to study 60 – 70 10
Marks percentage is same among all students? 70 – 80 30
OR
80 – 90 20
Marks percentage is varying among all students?
90 – 100 10
SIMPLE OR ONE-WAY TABLE
When the data are tabulated to one characteristic, it is said to be simple tabulation
or one-way tabulation.
In related variables, One IV and One or more DV can be used in One way Table
Example: Tabulation of data on population of world classified by one characteristic
like Religion, is an example of simple tabulation.
ONE WAY TABLE
Which represent one characteristic of the population, such as follows.

Marks % age No. of Students

50 – 60 20
60 – 70 Variables
10
70 – 80 30
80 – 90 20
90 – 100 10
 TWO WAY TABLE

A two-way table is a type of table that displays the

two independent categories on which the variables are
dependent.
To get more visibility, break apart the data and show
separately on second independent variable in a two-
way table
TWO WAY TABLE
Give information of two characteristics of the population. The Data is as follows:

Marks % age Gender Distribution

Male Female
50 – 60 5 15
60 – 70 5 5
70 – 80 15 15
80 – 90 15 5
90 – 100 2 8
COMPLEX OR MULTI-WAY TABLE
When the data are tabulated according to many characteristics (generally more than
two), it is said to be complex tabulation.
Example: Tabulation of data on population of world classified by three
characteristics like religion, nationality and literacy etc.
COMPLEX OR MULTI-WAY TABLE
Give information of three characteristics of the population. The Data is as follows:
Gender Distribution
Male Female
Marks % age
Pakistani Non- Pakistani Non-
Pakistani Pakistani
50 – 60 3 2 10 5

60 – 70 2 3 1 4

70 – 80 10 5 13 2

80 – 90 14 1 3 2

90 – 100 2 0 6 2
WHICH TABLE IS
SUITABLE HERE?
GRAPHS - DIAGRAMS
DIAGRAMATIC REPRESENTATION OF DATA
It is the representation of data in the form of diagrams. There are three types of
representation.

1. Dimensional diagrams / Graphs

2. Pictograms

3. Cartograms
HERE IS A DATA…
 Graphs

Line Graphs Histograms – Scatter Barchart Pie-charts Maps Box plots

polygons

Arithmetic Histograms Simple bar Spot Map

Scale chart

Semilogarithmic Frequency Grouped bar Area Map

Scale Polygons chart

Cumulative Stacked bar

Frequency chart

Component
bar charts
QUERY
If authorities ask me, show the composition of gender
variable in a graph? Which graph you will choose?
A. Stacked Bar chart
B. Simple Bar Chart
C. Multiple Bar Chart
D. Pie Chart
QUERY
If authorities ask me, compare the categories of gender
variable in a graph? Which graph you will choose?
A. Stacked Bar chart
B. Simple Bar Chart
C. Multiple Bar Chart
D. Pie Chart
BAR CHARTS
Bar graphs (or charts) are displaying information using only one coordinate.
Bar graphs are suitable for displaying data with categorical (qualitative) variable.
They are also used to compare discrete data in distinct categories.
RULES OF BAR DIAGRAM
a) Draw X-axis and Y-axis

b) Arrange data in ascending or descending orders.

c) Always take independent variable on X-axis

d) And dependent on Y-axis.

e) Draw the appropriate bars to represent the data.

f) If your data is very large then represent it in single lines all bars should be of proper size.
 SIMPLE BAR DIAGRAM
Simple bar chart - Compare size or frequency of different categories of a single variable

Colors No of Children

Red 8

Blue 7

Green 5

Yellow 9

Pink 6
 No of Children
10

0
Red Blue Green Yellow Pink
Red Blue Green Yellow Pink
 MULTIPLE BAR DIAGRAM
Compare size or frequency of different categories of 2 4 series of data

Represent data in adjacent multiple bars, these bars are kept side by side,
when you represent data of more than one item or two items.
Cities Educational institutions
No. of Schools No. of Colleges
27 20
Lahore
16 14
Islamabad
10 5
Faisalabad
5 4
Karachi
3 2
Sialkot
 Comparison of Colleges and Schools in different
cities of Punjab
30

25

20

15 No. of Schools
No. of Colleges

10

0
Lahore Islamabad Faisalabad Karachi Sialkot
 COMPONENT BAR DIAGRAM:
Compare how components Sports Gender
contribute to the whole in Boys Girls
different groups
Football 3 6
This is a diagram in which you
Hockey 2 2
divide a single bar into
multiple components. Rugby 5 1

It is good to represent data Other 2 1

where you have two
components and their total.
 Favorite sports
10
9
8
7
6
5
4
3
2
1
0
Football Hockey Rugby Other
Boys Girls
 PIE CHART - DATA WITH DISCRETE CATEGORIES
A pie chart is a circular chart that is split into segments
which show components of a larger group.
Pie charts are suitable for displaying categorical
(qualitative) data, or discrete data in distinct
categories.
The size of a given "slice" is proportional to the amount
of data (e.g. number of cases) it represents.
It is useful to order the components by decreasing or
increasing magnitude.
QUERY
If authorities ask me, show the distribution of variable in a
graph? Which graph you will choose?
A. Stacked Bar chart
B. Histogram
C. Circular Area Chart
D. Multiple bar Chart
QUERY
If authorities ask me, show the rate of change in variable in
a graph? Which graph you will choose?
A. Simple Bar chart
B. Histogram
C. Pie Chart
D. Scatter Plot
 HISTOGRAMS- RATES OR NUMBERS OVER TIME
 A histogram shows the frequency distribution of numerical data, either continuous
(such as height) or discrete (such as mortality).
 For example, number of cases during epidemic (epidemic curve) or over longer
period of time

It is used to represent :
 Numbers or rates over time
 Continuous data other than time series
Histograms can help visualize gaps in the data, outliners or other unusual
observations.
EPIDEMIC CURVE
In epidemiology, histograms are frequently used to present occurrence (distribution)
of onsets of illness according to time.
This is frequently called an epidemic curve even if it is not a curve.
DIMMENSIONAL DIAGRAMS:
There are commonly three types of dimensional diagrams present?

1. One dimensional?

2. Two dimensional?

3. Three dimensional?
 BOX PLOTS
Visualize statistical
characteristics
(median, range,
asymmetry) of a
variable’s
distribution
MAPS - CARTOGRAMS
Spot map Area map
Show location of cases or events Display events or rates geographically

When to use this type of map When to use this type of map
Place data Place data
Numbers Numbers or Rates
Specific site important  Specific site unimportant
Summary
If data are: And these conditions apply: Then use:
Numbers or rates over time Numbers/ Rates Histogram

Continuous data other than time Frequency distribution Histogram

series

Data with discrete categories Bar chart or pie chart

Place data Numbers •Specific site important Spot map

•Specific site unimportant Area map

Rates Area map

THANKS