CSE 2027-Fundamental of Data Analysis

Module: 4: Data Visualization and Charting

Types of charts and their significance, Organize data

interactively with tables , Visualizing data with charts,
Analyzing data with pivot tables, Build presentation
ready dashboards and turn real world data into
business insights, Tracking trends and making
forecasts, Interpretation and report writing.
 Introduction to Excel Data
Visualization
• Excel is widely used for data analysis owing to the excellent data visualization
features that it offers. The data visualization capability of Excel allows building
insightful visualizations.

2
 Various Types of Visualizations in
Excel
Every chart in Excel has its own significance. Excel provides a good
number of built-in charts, which can be beautifully leveraged so as to
make the right use of data.
• 1. Column Chart
It is a very simple chart type that presents data in the
form of vertical bars. First, to build a column chart,
select the data, and then select the required option
from the Column chart option, as can be seen below.
As we can see, various options are there in the
Column chart, and the requisite one should be
selected.

4
5
When we follow the above procedure, a column chart is created, as shown
in the below screenshot. It is a very simple column chart that gives us

region-wise total sales. The chart can be formatted as needed .

6
2. Line Chart
• This chart is useful for observing trends. E.g. in this
case, we have quarter wise data for two cities, and
we shall compare the sales trend over the quarters
for these two cities. First, to build a line chart, select
the data, and then select the requisite line chart
option as shown below.

7
8
• Following the above procedure leads to the creation
of a line chart, as shown below:

9
3. Pie Chart
• Pie Chart gives the contribution of a category, e.g.,
we shall build a pie chart to determine each
quarter’s percentage contribution in total sales. To
create a pie chart, select the requisite columns, and
click on the required pie chart option from the Pie
option as shown below.

10
11
• As a result of following the above procedure, a pie chart is created,
which can be seen below. The pie chart gives us a quick insight into
the percentage contribution.

12
4. Bar Chart
• This chart type is no different than a column chart,
only that here we have horizontal bars. In order to
build a horizontal bar, select the requisite bar chart
option from the Bar option as shown in the
following screenshot.

13
14
• As we can see in the above screenshot, we selected
clustered bar in 3-D, which gave us a clustered 3-D
bar graph, as shown in the following screenshot.
Using this visualization, we can compare sales for
three cities for four quarters.

15
5. Area Chart
• This chart represents the trend of a measure for
various categories over a period of time. The chart
makes use of areas to present the data. In order to
generate an area chart, we shall follow the steps as
mentioned in the below screenshot.

16
17
From the Area option, selected the requisite Area chart
option. As a result, we got the following chart, as shown
by the following screenshot. The area chart gives us a
quick insight into the sales trend over the quarters for the
three cities.

18
6. Scatter Chart
• This chart helps in determining the relation between
two variables. It is also referred to as the X-Y chart.
The chart requires two series and takes individual
corresponding values as x and y coordinates. In
order to build a scatter plot, first, select the data and
then select the requisite scatter plot option, as can
be seen in the following screenshot.

19
20
• Following the above procedure leads to the creation of a
scatter plot. As we can see, the pattern formed by the
scatter plot allows us to derive insights based on the
context.

21
7. Stock Chart
• These are special types of charts that are used for
stock price analysis. In order to build a stock chart,
select the data and select the requisite stock chart
option, as shown in the following screenshot.

22
23
• As can be seen in the above screenshot, Open-High-
Low-Close stock chart. This chart requires that the
Opening Price, High Price, Low Price, and Closing Price
of stocks must be defined in the order. Each of the chart
options in the Stock chart requires a different set of
inputs. When the chart is built, it looks like as shown
below.

24
8. Doughnut Chart
• This chart is a type of pie chart, only that it is represented
in the shape of a doughnut. Building this chart is quite
simple. Select the data over which the chart needs to be
built, and then from the other chart option, select the
required option from the two doughnut options. This is as
shown in the below screenshot.

25
26
• The above procedure leads to the creation of the doughnut
chart, which is as shown below. The doughnut chart gives
us an idea of the average % contribution in total sales. The
middle space in the doughnut chart can be used to write a
meaningful text that conveys some insight.

27
9. Bubble Chart
• Bubble charts, though complex, can be beautifully
used to derive insights from data. This chart takes
into consideration three values.
• Two of the three dimensions are used for
representing X-axis and Y-axis, respectively, and the
third value determines the size of the bubble. We
shall build a bubble chart using the method as
illustrated below.

28
29
• As can be seen in the above screenshot, we selected
a bubble chart with a 3-D effect. Note that we
selected numeric data only from the table for
building the bubble chart, which can be seen in the
screenshot. When we follow the above method, we
get a bubble chart, as shown below.

30
Organize data interactively with
Tables
• Data Tables: The most common way of looking at data is through a
table, where the raw data is displayed in familiar rows of observations
and columns of variables. It is essential for reviewing the raw data

31
Organize data interactively with
Tables
• Contingency Tables : Also referred to as two-way cross-classification tables
provide insight into the relationship between two variables. The variables must
be categorical or transformed to a categorical variable.

32
Organize data interactively with
Tables
• Summary Table: A summary table (or aggregate table) is a common way of
understanding data. Summary tables will often show a count of the number of
observations (or percentage) that have that particular value (or range).
• Any number of other variables can be shown alongside. Since each row now
refers to a set of observations, any other columns of variables must now contain
summary information. Descriptive statistics that summarize a set of observations
can be used.

33
Organize data interactively with
Tables
• An ordered array is a sequence of data, in rank order, from
the smallest value to the largest value

34
Organize data interactively with
Tables
 The frequency distribution is a summary table in which the data are
arranged into numerically ordered class groupings.

 You must give attention to selecting the appropriate number of class

groupings for the table, determining a suitable width of a class grouping,
and establishing the boundaries of each class grouping to avoid
overlapping.

 To determine the width of a class interval, you divide the range

(Highest value–Lowest value) of the data by the number of class
groupings desired.

35
Organize data interactively with
Tables
Example: A manufacturer of insulation randomly
selects 20 winter days and records the daily high
temperature

24, 35, 17, 21, 24, 37, 26, 46, 58, 30, 32, 13, 12, 38, 41, 43, 44,
27, 53, 27

36
37
38
 Organize data interactively with
Tables
• Cumulative frequency tabulation is performed from a
frequency table by adding each frequency to the total of
frequencies of all data values before it in the data set.

39
Visualizing Data with Charts

40
Visualization: Principles of
Excellent Graphs
• The graph should not distort the data.
• The graph should not contain unnecessary
adornments (sometimes referred to as chart junk).
• The scale on the vertical axis should begin at zero.
• All axes should be properly labeled.
• The graph should contain a title.
• The simplest possible graph should be used for a
given set of data.

41
Graphical Errors: Chart Junk

42
Graphical Errors: Compressing
the Vertical Axis

43
Analyzing Data With Pivot Tables
If you want to see at a glance the trends, patterns, and meaning behind
your data, then PivotTable reports are for you.
Imagine an Excel worksheet of company sales figures with thousands
of rows of data. Everyone has questions about what the data means.
How do you get answers quickly and easily?

PivotTable reports summarize and organize data into different views

that present comparisons, reveal patterns and relationships, and
analyze trends. Let’s find out how PivotTable reports make it so easy.

44
Analyzing Data With Pivot Tables
•With a PivotTable report, you decide what data you
want to be analyzed, and how to organize it.

•Instead of a single arbitrary form that doesn’t really

suit your needs, each PivotTable report gives you a
different view of your data that is customized to your
purposes and answers your questions on the spot.

45
Analyzing Data With Pivot Tables
•Creating a PivotTable report is about moving
pieces of information around to see how they fit
together.

•Not satisfied with the first report? It just takes a

couple of seconds to pivot rows and columns into a
different arrangement, a bit like turning a
kaleidoscope to see different patterns.

46
Pivot Table: Example

47
Pivot Table: Example

48
Pivot Table: Example

49
Pivot Table: Example

50
Pivot Table: Example

51
Pivot Table: Example(Animated)

52
Pivot Table: Example

53
Pivot Table: Example

54
Build presentation ready dashboards
1.Organize data - The most important part is to
have all the information you plan on graphing in
one area. It can be very hard to link the graphs if
data is spread out throughout the spreadsheet
2.Set up page - The orientation can be landscape
or portrait, and the size will depend on the
output you’re trying to create. The most
common is to make it an 8.5” by 11” page so that
it can easily print to paper or PDF in a standard
size

55
Build presentation ready dashboards

3.Brainstorm – Experiment and tinker to finally

come up with a great design. This step usually
takes several iterations, and may even
continually change and get updated based on the
feedback received over time
4.Select visuals – Choose the right type of charts

56
Build presentation ready dashboards
5.Focus attention – Create comments, arrows, use
appropriate colors to draw attention to
information
6.Tell a story - make sure it tells a compelling story.
Is it painting the picture you want it to? This is
when you step back and take a bird’s-eye view of
your data, the key messages, and compare that to
the original purpose of the dashboard.

57
Example: Corporate Dashboard

58
Turn real world data into business
insights

59
 Making Forecasts
Many types of models differ in complexity & amount of data & way
they generate forecasts:
1. Forecasts are rarely perfect
2. Forecasts are more accurate for grouped data than for
individual items
3. Forecast are more accurate for shorter than longer time
periods

60
Making Forecasts
• Decide what needs to be forecast
• Level of detail, units of analysis & time horizon
required
• Evaluate and analyze appropriate data
• Identify needed data & whether it’s available
• Select and test the forecasting model
• Cost, ease of use & accuracy
• Generate the forecast
• Monitor forecast accuracy over time

61
Interpretation and Report Writing
Most Important Things to Remember About Data Analysis
•Develop a plan before you analyse data.
•Develop some dummy tables or lists to hold your analysed data –
share those with others.
•Identify the most important findings from your data, summarize them
and then use the specific results (e.g., a table or list of data) to clarify
your findings.
•Present your analysis in an orderly, meaningful, simple way.

62
Interpretation and Report Writing
Things to Avoid When Analysing Data

1. Including response rates and problems with your methodology as

part of your findings.
2. Reporting both numbers and percentage unless one is needed to
make the other clear.
3. Listing in a sentence or a table, all of the response choices for every
question on a survey in the order they appear on the survey. [Don’t do
this with interview data either]
4. Report your results with excessive precision – most of the time you
can just round to the nearest whole number when reporting
percentages.

63
Interpretation and Report
Writing
5. Feel compelled to keep your results in the same order as they
appeared on the survey or the interview protocol. It is the job of the
analyst to order things in the best way to clarify the findings – you are
NOT REQUIRED to present things in the order you asked them.
6. Do not include any action steps or conclusions that are not clearly
developed from your findings.

64
Interpretation and Report Writing:
Rules for a Good Report
1. Follow the report writing outline in your manual. Feel free to be somewhat
flexible with the order, but don’t leave out whole sections.
2. Make your own internal outline including who is responsible for which
sections. Be sure that you leave time for stakeholders to help you with
editing/making revisions.
3. Be economical in your decisions about what to include in your report. Shorter
is better.
4. Avoid excessive use of jargon.
5. Read your work – if you can’t understand it, chances are others won’t be able
to either. Think, in simple terms, about what you are trying to say, and then write
that.
6. Use complete sentences and standard English grammar conventions. You can
rely some on bullets and be limited in your transitions, but be sure your reader
can follow your logic.

65
Interpretation and Report Writing:
Rules for a Good Report
7. Use headers and sections to help your reader know what is happening in
your report. Be consistent about where and how they appear (centered, bold,
underlined, side headings etc.). NUMBER THE PAGES.
8. Use tables and Graphs to help illustrate findings. ALL TABLES AND GRAPHS
MUST HAVE TITLES, LABELS AND LEGENDS OR FOOTNOTES SO THAT THEY
STAND ALONE.
9. Use quotes and vignettes or snippets from field notes to illustrate your
findings. Remember quotes should have quote marks around them and be
attributed to the speaker or writer.
10. Be consistent in your use of language, capitalization, punctuation etc. For
the most part, evaluation reports should be written in the past tense – only
report what you actually did and what you found.
11. Do not introduce totally new topics into your report in the final sections.

66
Sample Data Analysis Report
Outline

67
Sample Data Analysis Report
Outline

Ref:
https://www.template.net/pro/10766/data-
analysis-report
68