The Trouble with Pie Charts

Data visualization experts will often show pie charts as an example of “bad” visualization. Xan Gregg (one of my colleagues at JMP) has posted the challenge “One Less Pie” for pie day, to show some better ways to visualize data.

But, you may ask, what’s wrong with pie charts?

Much smarter people have already answered this question, but let’s take a look at a “real” example from the recent “Transmedia Survey” (run by the unstoppable Team Thielbar/Dansky).

One of the first questions we asked in that survey was “Of the books you purchased last year, what percent were e-books?” We could show the results using a pie chart, like so:


However, the pie chart loses the ordering. It’s not obvious in the resulting chart that “Less than 20 Books” is ordered next to “20 – 50”. A better visualization, like a share chart (or a stacked bar), shows the proportions without losing the ordering:


This gets more important as you add information to the visualization. Maybe we want to see if people who play video games buy more, less, or the same number of e-books as people who don’t. Which visualization would you prefer for that question?

Pie chart?


Or Share Chart/Stacked Bar?


I prefer the stacked bar graph because it lets you compare the proportions across groups easily and quickly. The information is more compact, and it communicates a lot more than scanning across four different pie charts.

There are places where a pie chart can work. For example, the “Do you want cool stuff?” question has a small number of levels, and there’s no real order to them. A pie chart communicates who said “yes” and who said “no” pretty easily:


As you might have guessed, the graphs shown are JMP graphs. The pie charts come from JMP’s Graph Builder, and the share carts are the default visualization in the Categorical Platform.

You can follow the further adventures of the pie chart on the JMP blog or by searching the hash tag #OneLessPie on Twitter.

About Melinda Thielbar

Melinda Thielbar is a co-founder of Research Triangle Analysts, Ph.D. statistician, spinner of fine yarn, martial artist, fraud analyst, and fiction writer. In other words, she's a polymath. Follow Melinda on Twitter @mthielbar, or join the Research Triangle Analysts group on G+ to join the conversation about data science.
This entry was posted in Uncategorized and tagged , . Bookmark the permalink.

One Response to The Trouble with Pie Charts

  1. Pingback: The Trouble with Pie Charts | analyticalsolution

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s