Selecting The Right Graph For Your Message - InformationWeek

InformationWeek is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

IoT
IoT
Software // Information Management
News
9/20/2004
01:32 PM
50%
50%

Selecting The Right Graph For Your Message

What's the right graph for your BI message? Here are practical ideas that remove the guesswork from successful data presentation.

This series on effective data presentation is about building a solid conceptual foundation for all of your presentations (see Resources). Although the number of possible messages is without limit, the universe of quantitative messages (the focus of this article) can be boiled down to seven quantitative message types. By simply identifying the message type and knowing the proper design solutions that correspond to that type, you'll be able to conquer most of your design choices. In other words, you'll apply a few general principles to countless specific data presentation challenges.

Almost every situation you'll encounter when presenting typical business information can be addressed using these seven quantitative message types. (Of course, you might encounter unique data presentation challenges in the specialized aspects of a particular business or in the scientific community. This article focuses on solutions for the data you'll encounter regularly across all businesses, regardless of industry.)

Before listing and describing these seven quantitative message types, however, I need to introduce two preparatory concepts: the difference between quantitative and categorical data, and the visual objects that can be used to encode quantitative values in graphs, including their differing strengths.

Quantitative and Categorical Data

Messages that involve quantitative data — the numbers that measure things — always include related categorical data as well. Categorical data identifies what the numbers measure: "Are these numbers measuring the productivity of individual employees, sales within regions, or shipments per day?" In a graph, categorical data appears as the text labels for the numeric values that appear in the space bounded by the axes. Simply put, categorical data tells us what and quantitative data tells us how much. Quantitative data without related categorical data is useless.

Categorical data sets consist of multiple items — subdivisions of the category. A region category might consist of north, south, east, and west. A time category might consist of the individual months of a year. A graph can include more than one set of categorical data. Take a moment to look at the two graphs in Figure 1 and count the number of categorical data sets in each.

The graph on the left has a single set of categorical data: time, subdivided into four quarters. The graph on the right has two sets of categorical data: time, subdivided into four quarters as on the left, and regions, subdivided into north, east, south, and west.

Whatever the category and its subdivisions, it is one of three types based on how the individual category subdivisions relate to one another. The three types are:

  • Nominal
  • Ordinal
  • Interval.

Just as we use the term scale to refer to the range of quantitative values that appear along an axis in a graph, we also refer to a set of categorical items arranged along an axis as a scale. Graphs always include at least one quantitative scale and almost always include one or more categorical scales, although I'll point out an exception a little later.

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Previous
1 of 4
Next
Comment  | 
Print  | 
More Insights
InformationWeek Is Getting an Upgrade!

Find out more about our plans to improve the look, functionality, and performance of the InformationWeek site in the coming months.

News
Remote Work Tops SF, NYC for Most High-Paying Job Openings
Jessica Davis, Senior Editor, Enterprise Apps,  7/20/2021
Slideshows
Blockchain Gets Real Across Industries
Lisa Morgan, Freelance Writer,  7/22/2021
Commentary
Seeking a Competitive Edge vs. Chasing Savings in the Cloud
Joao-Pierre S. Ruth, Senior Writer,  7/19/2021
White Papers
Register for InformationWeek Newsletters
Video
Current Issue
Monitoring Critical Cloud Workloads Report
In this report, our experts will discuss how to advance your ability to monitor critical workloads as they move about the various cloud platforms in your company.
Slideshows
Flash Poll