StATS: Three dimensional bar and pie charts (February 21, 2006)

I often get asked to review research papers and posters that people here at the hospital produce, and I am always glad to do so. Sometimes these papers and posters have me listed as a co-author, so I have even more incentive to do a careful review.

Once in a while, a paper or poster will have a graphical presentation of data that includes a bar chart or pie chart that includes a fake three dimensional dimension that exists solely to make the data look more impressive. This is something I always discourage. The three dimensional effect almost always makes it more difficult to read numbers off of the chart and to make comparisons. A two dimensional chart works much better.

I did have a stock talk that I gave on this topic, but it has been lost to time and I need to find a way to resuscitate it. Several sections of this venerable talk have been repackaged into the following web pages:

• Stats: Pitch the pie! Ban the bar!
• Stats: Displaying tables of percentages
• Stats: Log transformation

but more work needs to be done.

A very nice beginners guide on how to layout tables and graphs properly is

• Presenting Numbers, Tables, and Charts. Sally Bigwood, Melissa Spore (2003) Oxford, England: Oxford University Press. [BookFinder4U link] (Model, Descriptive, Graphics)

These authors also have a nice website:

• Plain Figures. Sally Bigwood, Melissa Spore. Accessed on 2005-04-15. (Model >> Graphics) [Excerpt] Plain Figures is a method of transforming numerical information into figures, tables and graphs that people readily understand. Plain Figures is an international consulting and training company that can make your statistical, financial and other data accurate, vivid and memorable. Our goal is to raise the standard of data presentation throughout the world - starting with you! Plain Figures is the subject of our book - Presenting Numbers, Tables, and Graphs published by Oxford University Press (2003). This useful guide puts Plain Figures methods and references at your fingertips. www.plainfigures.com

In the meantime, here are some web resources that decry the use of fake three dimensional effects.

• 2-D or not 2-D? (That is the question). Reynolds G, Published January 16, 2006 at Presentation Zen, Garr Reynolds' blog on issues related to professional presentation design. Accessed on 2006-02-21. [Excerpt] We can learn how to be better presenters by observing the masters. I often say, for example, that we can improve our presentations by emulating certain aspects of Steve Jobs' presentation style. Today, though, I'd like to talk about one aspect of Steve's presentation Tuesday that we can learn from by not emulating. And that is the use of 3-D charts to represent 2-D data. presentationzen.blogs.com/presentationzen/2006/01/2d_or_not_2d_th.html
• How to Construct Bad Charts and Graphs. Klass G, Department of Politic and Government, Illinois State University, copyright 2002. Accessed on 2006-02-16.  [Excerpt] The three fundamental elements of bad graphical display are these: Data Ambiguity, Data Distortion, and Data Distraction. lilt.ilstu.edu/gmklass/pos138/datadisplay/badchart.htm
• The 10 Comandments for Figures. Head K, Sauder School of Business, University of British Columbia. Accessed on 2006-02-16. [Excerpt] If you need to satisfy me because I'm your prof or you think I might be a referee, then just follow the rules. If you want more information about the rationale behind the rules, they are mainly based on the books by Edward Tufte which are really worth reading for the examples and interesting discussion. pacific.commerce.ubc.ca/keith/figcoms.htm
• Misleading visualizations. Ingo H. Accessed on 2006-02-16. [Excerpt] The Post-Enron world with it's tough requirements on reliable financial reports has left US accountants and CEOs without choice. They will now have to tell us the truth and nothing but the truth about their companies financial status. Or do they? While the art of creative accounting may have come to an end when it comes to the actual numbers in the the book, there are still other ways in which a financial report could mislead it's reader into believing that everything is going great. This paper suggests various ways to make "better than reality" charts, while at the same time preserving correctness with the underlying statistics. Each technique is briefly evaluated in terms of a lie factor and whether or not it fulfils the requirement of embellishing the truth while at the same time not getting caught. Some real world examples are also evaluated in the same way. avoinelama.fi/~hingo/kirjoituksia/misleadingvisualizations.html
• Gallery of Data Visualization. Friendly M, Statistical Consulting Service and Psychology Department, York University. Accessed on 2006-02-16. [Excerpt] Like good writing, good graphical displays of data communicate ideas with clarity, precision, and efficiency. Like poor writing, bad graphical displays distort or obscure the data, make it harder to understand or compare, or otherwise thwart the communicative effect which the graph should convey. This Gallery of Data Visualization displays some examples of the Best and Worst in statistical graphics, with the view that the contrast may be useful, inform current practice, and provide some pointers to current work. The term "Data Visualization" means rather different things to people in disciplines. The emphasis here is somewhat more on the Statistical Graphics side than on the side reflected in, say, the comp.graphics.visualization newsgroup. Do you know of other examples of the Best or Worst in Statistical Graphics on the Web? Let me know through this Image submission form. The page is organized as a collection of images, along with a few of the 1000 words each may be worth and some links to original sources. To reduce transmission time, most of the images are presented as thumbnails, with links to larger originals. Click on the thumnail image or on the words "Full size". ricardo.ecn.wfu.edu/SCS/Gallery/

And here is a dissenting voice, of sorts.

• Visualization for Communication: The Importance of Aesthetic Sizzle [PDF]. Brath R, Peters M, Senior R, Oculus Info Inc. Accessed on 2006-02-16. [Excerpt] When creating a visualization for communication, the inclusion of aesthetically appealing elements can greatly increase a design’s appeal, intuitiveness and memorability. Used without care, this “sizzle” can reduce the effectiveness of the visualization by obscuring the intended message. Maintaining a focus on key design principles and an understanding of the target audience can result in an effective visualization for communication. This paper describes these principles and shows their use in creating effective designs. www.oculusinfo.com/papers/VisualizationSizzleForCommunication-clrFinal.pdf

All of these sites pay homage to Edward Tufte, who has made a very persuasive case for good statistical graphics in the books he has published:

• The Visual Display of Quantitative Information. Tufte ER (1983) Cheshire, CT: Graphic Press. ISBN: 096139210X. [BookFinder4U link]
• Envisioning Information. Tufte ER (1990) Cheshire, CT: Graphics Press. ISBN: 0961392118. [BookFinder4U link]
• Visual Explanations: Images and Quantities, Evidence and Narrative. Tufte ER (1997) Cheshire, CT: Graphics Press. ISBN: 0961392126. [BookFinder4U link]

There's a second edition of the 1983 classic that has come out, but I don't have it yet. Dr. Tufte is also working on a new book, Beautiful Evidence, but I have no details about it.

It's also worthwhile to visit Dr. Tufte's web site.

• The Work of Edward Tufte and Graphics Press. Tufte ER. Accessed on 2006-02-16. [Excerpt] Edward Tufte has written seven books, including Visual Explanations, Envisioning Information, The Visual Display of Quantitative Information, and Data Analysis for Politics and Policy. He writes, designs, and self-publishes his books on information design, which have received more than 40 awards for content and design. He is Professor Emeritus at Yale University, where he taught courses in statistical evidence, information design, and interface design. His current work includes digital video, sculpture, printmaking, and a new book Beautiful Evidence. This website describes Edward Tufte's books, one-day course, and artwork. www.edwardtufte.com/tufte/

Finally, Edward R. Tufte has written the definitive critique of PowerPoint

• The Cognitive Style of PowerPoint. Tufte ER (2003) Cheshire, CT: Graphics Press. ISBN: 0961392150. [BookFinder4U link]

which is not relevant to this weblog entry, but I can't resist the temptation to bash Powerpoint, and bash it again. Still I did offer equal time to a defender of PowerPoint.

This page was written by Steve Simon while working at Children's Mercy Hospital. Although I do not hold the copyright for this material, I am reproducing it here as a service, as it is no longer available on the Children's Mercy Hospital website. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Category: Descriptive statistics.