![]() ![]() ![]() The ‘box’ segments in each box-and-whisker shape, then, look like they represent more of something than the ‘whisker’ segments, leading to the faulty interpretation that they contain more values, or perhaps have more importance. If you’re a human with normal vision, you intuitively perceive thick, wide shapes as representing greater quantities (of whatever) than thin, narrow shapes. ![]() ![]() Let’s have a closer look at each of these problems in turn: The design of traditional box plots doesn’t make ‘visual sense.’īox plots are needlessly hard to grasp because their visual design doesn’t align well with how the human visual system works, i.e., they don’t make ‘visual sense.’ Specifically, I see three problems with the visual design of traditional box plots: Box plots conceal information that’s usually crucial to see.Box plots require audiences to grasp complex concepts that they don’t need to understand in most cases.The design of traditional box plots doesn’t make ‘visual sense,’ which makes them unnecessarily hard to learn how to read and prone to misinterpretation.What, exactly, are those flaws? I see three significant ones, which I’ll examine in detail: These issues arise from what I see as flaws in the traditional box plot design, which was first proposed by Mary Spear in 1952 and refined by dataviz legend John Tukey in 1969 (I can feel the flames licking at my heels already). Even when audiences are familiar with box plots, they still require excessive, unnecessary cognitive gymnastics to interpret compared with alternative chart types such as strip plots and distribution heatmaps (see examples below), and are prone to misinterpretation.People struggle to grasp box plots much more than other “fundamental” chart types, and more even than “complex” chart types like scatterplots or histograms.Among participants in my workshops-who generally have above-average graphicacy levels to begin with-typically less than 20 percent already know how to read box plots. Most people don’t know how to read box plots.Let me share a few observations from my experiences explaining how to read box plots to thousands of workshop participants over the years: I can read box plots just fine and so can the audiences for my charts.” “I have no idea what you’re talking about. In my experience, though, virtually all the types of insights that chart creators try to communicate using box plots can be communicated using simpler, more familiar, and, frankly, better-designed chart types that don’t require audiences to slog through a multi-minute comprehension process beforehand. If a chart type requires that much time to explain, it had better deliver a huge “epiphany payoff,” as data storytelling expert Brent Dykes calls it, i.e., it had better deliver valuable insights that can’t be communicated using simpler, more familiar chart types that require less time and effort for the audience to understand. Why not? Well, if you watched the explanatory video linked above, you saw that it took me over four minutes to explain how to read a box plot. I used to use box plots often, but I rarely use them now. Not sure what a box plot (a.k.a., a “box-and-whisker plot”) is or how to read one? If so, you should watch this explanatory video before continuing. Alternative chart types are virtually always easier to learn how to read, more informative, or both. This has caused innumerable distribution-based insights to fail to land with audiences who weren’t willing or able to grasp them. Tl dr: After having explained how to read box plots to thousands of workshop participants, I now believe that they’re poorly conceived (box plots, not workshop participants □ ), which makes this classic chart type unnecessarily unintuitive, hard to grasp, and prone to misinterpretation. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |