Why data storytelling?

Data is useless until we understand what it means and can clearly communicate that meaning to those who need it. We live in the information age where there is so much information available and without proper care and skill, we can easily drown it.

Above all else, this article focuses on the communication of data via storytelling. Data storytelling is the process of displaying data in a visual context to communicate patterns, trends, or summaries of the data.

Studies have shown that our mind is constantly trying to sort and group objects in order to draw conclusions. Academic studies in this field started in the early 1900s and continue to inform data presentation in Business settings today.

As some evidence of this, academic researchers and the Teradata University Network ran a study to determine the state of business intelligence and analytics. They asked over 400 recruiters from technology companies to respond to the following prompt.

“When I recruit for business intelligence, data analyst, business analyst roles, it is important that the individuals or students have the following knowledge.” The recruiters had to rank a bunch of possible responses. Here is an overview of the rank system for their most preferred skill:

1. Communication skill
2. SQL & query skill
3. Basic analytics skill

We can infer from this study that the ability to communicate your data effectively ranks above being able to pull data from a database and is even more important than analytical skills.

Why does data visualization matter?

Effective data visualization helps an audience analyze, understand & draw conclusions through the summarization of data. It can mean the difference between success and failure when it comes to communicating the findings of your study, raising money for your business, presenting to your board or investors, or simply getting your point across to your audience. Visualization is simply all about making complex insights simple and this is done with the use of images, texts, charts, and tables.

Here is a PowerPoint file that serves as a detailed and informative guide on why effective data visualization is the essence of sage communication.

Download data visualization 101 file 149 Downloads

Uses of illustrative Charts and Table summaries

The following are the uses of charts and table summaries for data visualization;

• Reporting
• Status updates
• Dashboarding

Let’s take a glance at some fundamental principles that govern how the human mind perceives objects.

Gestalt principles of visual perception

The human brain is wired to see structure, logic, and patterns. It helps us make sense of the world. In the 1920s a group of German psychologists developed theories around how people perceive the world around them, called Gestalt principles. These principles are;

Similarity

When objects are similar in shape, and color we perceive them as a group.

Anomaly

This is when an opposite object becomes the focal point(an alert, a call) in a group of similar objects.

Closure

When there are spaces, we naturally tend to want to close it so that we see uniformity.

Pragnanz

The word pragnanz is a German term meaning “good figure.” The law of Pragnanz is sometimes referred to as the law of good figure or the law of simplicity. This law holds that objects in the environment are seen in a way that makes them appear as simple as possible

Enclosure

When objects are enclosed by a visual aid such as a line, color, shape, or borders they are perceived to belong to a group.

Continuity

The law of continuity holds that points that are connected by straight or curving lines are seen in a way that follows the smoothest path. Rather than seeing separate lines and angles, lines are seen as belonging together.

Proximity

Objects that are placed close together will be seen as part of a group.

Alright, you now know the basic principles of design which helps improve the user experience.

Selecting an effective visual

When you want to communicate your data to your audience, you have to be specific about what you want to explain, the specific story you want to tell. The more specific you can be about who your audience is, the better position you will be in for successful communication.

"Above all else, show the data".
Edward Tufte

Ask yourself these two questions whenever you want to visualize your data;

1. What do you need your audience to know?
2. What data is available to help convey your point?

Recommendations for effective data visualization

The following are pragmatic best practices to serve as guidelines for effective data visualization. They are:

• Be simple i.e. less is more
• Use intuitive titles and labels
• Use callouts i.e. use color contrast or size to draw the audience's attention
• Use color intentionally i.e. resist the urge to just be colorful
• Understand the constraint of the medium i.e. the chart limitation
• Remove chart junk i.e. nonessential information in a chart

"Power corrupts, PowerPoint corrupts absolutely." Edward Tufte

Yes! we are approaching the grand finale, hang in there.

Effective data visualization samples

If you wish to tag along and recreate these samples, you should download the dataset using the link provided below:

Download practice file here 128 Downloads

Note: The visuals that we will be creating are under the context of live presentations and not for dashboards. i.e. Best practice is seldom equivalent to common practice.

Creating effective visuals

We are going to make use of the most commonly used charts for data visualization to tell our story and illustrate best practices for data visualization using the Vanni Delivery Sales workbook as a case study.

Line Chart

This is used for showing continuous data eg. units of time such as days, months, quarters, years, etc.

Steps to inserting a line chart

The following are the steps to insert a line chart:

1. Click on a cell within the dataset
2. Navigate to the Insert tab and select the Pivot table option
3. Drag the Date and Revenue fields into the Rows and Values fields respectively
4. De-select the years and quarters hierarchy and show only months
5. Format Pivot table appropriately
6. Click on any cell within the Pivot Table
7. Navigate to the Insert tab and select Line chart from the charts group

Pivot Table

Line chart

Line chart

"If the information is important, it must be well communicated."
Stephen Few

Horizontal Bar Chart

It is best used for Item comparisons. Categorical data are organized into groups. Our eyes compare the relative endpoints of the bar.

Steps to inserting a bar chart

The following are the steps to insert a Bar chart:

1. Click on any cell within the dataset
2. Navigate to the Insert tab and select the Pivot table option
3. Drag the Department and Population fields into the Rows and Values fields respectively
4. Format Pivot table appropriately
5. Click on any cell within the Pivot Table
6. Navigate to the Insert tab and select Bar chart from the charts group

"Clutter is your enemy, above all else, good design takes into account the needs of the user."
Cole Nussbaumer Knaflic

Pivot table

Horizontal Bar chart

Vertical Bar / Column Chart

Similarly, a column chart is a data visualization where each category is represented by a rectangle, with the height of the rectangle being proportional to the values being plotted. Column charts are also known as vertical bar charts.

Steps to inserting a Column chart

The following are the steps to insert a Column chart:

1. Click on any cell within the dataset
2. Navigate to the Insert tab and select the Pivot table option
3. Drag the Month and Rainfall(mm) fields into the Rows and Values fields respectively
4. Format Pivot table appropriately
5. Click on any cell within the Pivot Table
6. Navigate to the Insert tab and select Column chart from the charts group

Pivot Table

Vertical Bar /Column Chart

Pie Chart

It is used best for showing composition, or parts of a whole. There are arguments against the use of this chart but it still has its merit.

Steps to inserting a pie chart

The following are the steps to insert a pie chart:

1. Click on any cell within the dataset
2. Navigate to the Insert tab and select the Pivot table option
3. Drag the Returns and Units fields into the Rows and Values fields respectively
4. Change the value field settings of the Units from SUM to show value as % of GRAND total
5. Format Pivot table appropriately
6. Click on any cell within the Pivot Table
7. Navigate to the Insert tab and select Pie chart from the charts group

Pivot Table

Pie Chart

100% Stacked Column chart

It is a variation of the Column chart. They are meant to allow you to compare totals across categories and also see sub-components of pieces within a given category

Steps to inserting a Stacked Column chart

The following are the steps to insert a 100% Stacked chart:

1. Click on any cell within the dataset
2. Navigate to the Insert tab and select the Pivot table option
3. Drag the Products and Revenue fields into the Rows and Values fields respectively
4. Change the value field settings of the Revenue from SUM to show value as % of ROW total
5. Format Pivot table appropriately
6. Click on any cell within the Pivot Table
7. Navigate to the Insert tab and select the 100% Stacked column chart from the charts group

Pivot Table

100% Stacked column chart

I hope you enjoyed going through the nuances of data visualization as much as I did. As always, the best way to become great at anything is to keep practicing. Practice! Practice! Practice!

Conclusion

A fitting crescendo to this article that was largely wrapped up in best practices on how to communicate your data efficiently to your end-user or audience without cluttering your work with non-essential information.

We do hope that you found this blog exciting and insightful, for more access to such quality content, kindly sign up to the Resa platform by clicking here.

Thank you for learning with Us!