Skip to content

That puzzle-solving feeling

Since this blog in November, I’ve given my talk on infovis vs. statistical graphics about five times: once in person (at the visualization meetup in NYC, a blog away from Num Pang!) and the rest via telephone conferencing or skype. The live presentation was best, but the remote talks have been improving, and I’m looking forward to doing more of these in the future to save time and reduce pollution.

Here are the powerpoints of the talk.

Now that I’ve got it working well (mostly by cutting lots of words on the slides), my next step will be to improve the interactive experience. At the very least, I need to allocate time after the talk for discussion. People usually don’t ask a lot of questions when I speak, so maybe the best strategy is to allow a half hour following the talk for people to speak with me individually. It could be set up so that I’m talking with one person but the others who are hanging out could hear the conversation too.

Anyway, one of the times I gave the talk, a new idea came out: One thing that people like about infovis is the puzzle-solving aspect. For example, when someone sees that horrible map with the plane crashes (see page 23 of the presentation), there is a mini-joy of discovery at noticing–Hey, that’s Russia! Hey, that’s India! Etc. From our perspective as statisticians, it’s a cheap thrill: the reader is wasting brainpower to discover the obvious. But I think most people like it. In this way, an attractive data visualization is functioning like a Chris Rock routine, when he says something that we all know, but he says it in such a fresh new way that we find it appealing.

Conversely, in statistical graphics we use a boring display so that anything unexpected will stand out. It’s a completely different perspective. I’m not saying that statisticians are better than infovis people, just that we strive for different effects.

Another example are those maps that distort the sizes of states or countries to be proportional to population. Everybody loves these “cartograms,” but I hate ’em. Why? Because the #1 thing these maps convey is that some states on the east coast have high population density and that nobody lives in Wyoming. People loooove to see these wacky maps and discover these facts. It’s like being on vacation in some far-off place and running into Aunt Louise at the grocery store. The shock of the familiar.

(I’m not opposed to all such maps. In particular, I like the New York Times maps that show congressional and electoral college results within stylized states that include congressional districts as little squares. These maps do the job by focusing attention on the results, not on the cool processes used to create the distortions.)


  1. DavidC says:

    I always think about 'cartograms' when I'm using colors to plot something on a map. I wonder if the large size of less important areas may distort the impression I (or others) get from the map. Maybe a cartogram would help? (Other ideas?)

  2. K? O'Rourke says:

    Micheal mair use to do work on verbal interaction trajectories

    If I rememebr correctly he found if the speakers trajectory was too predictable to the listener, the listener would lose interest and the same for too unpredictable – there seemed to be an optimal level of unpredictability for maximum engagement.

    A quick web search found this


  3. Antony Unwin says:

    Improving the interactive experience, a.k.a. getting discussion going, is often hard but always worthwhile. If I was there i would give you some discussion! Our interchanges preparing the material were productive and entertaining without resolving all our differences, in particular the issue of statistical graphics v. data visualisation.

    Intepreting interactive another way, maybe you can now be persuaded to make some serious use of interactive graphics. Interaction could help move the debates about how to draw graphics more in the direction of which graphics to draw.

  4. Rob says:

    I find that you have to be very careful showing any kind of data representation (or any visual for that matter). First off, your audience will automatically be attracted to any visual you put out there. In effect, you are directing all the attention that was once on you, onto a picture.

    If your visual is too creative (like some cartograms), then your audience will become distracted and will lose the message behind the visual.

    When I present, I often make my visuals as plain as possible so that (at first) it doesn't like much. The audience will then direct their attention back to me, and then I explain why the visual is important/related to the research / topic of the presentation. It isn't until then that the audience realizes that (while visual is boring), it is a valuable part of the presentation.

    By doing it this way, your audience now understands the message of the visual; not just intrigued by a creative cartogram-like design.

  5. This is an interesting analysis, but unfortunately you're mostly hitting strawmen. Your view of visualization seems to be limited to what FlowingData and infosthetics post, which is mostly infographics and artistic visualization (and a lot of stuff that's pretty and colorful but hardly visualization).

    Your whole argument about puzzles therefore does not apply to most serious visualization. You should check out some of the work presented at VisWeek, EuroVis, and other conferences, to see what visualization really is about, and how much closer to statistical graphics it is than you think.

    There is still a lot the visualization community can learn from statistics (and vice versa), and we'll need good critiques to make us more aware of our issues. But such a critique needs to actually hit the real problems (and there are plenty), not just focus on a skewed sample from two websites.

  6. Andrew Gelman says:


    You're probably correct and I'd like to discuss this further. But, just for a couple quick responses:

    – Flowing Data is written by a statistician and appears to have about 3 times as many readers as this blog. So when he publishes a list of "5 best data visualizations," I have to think that this represents an influential view of what statistical graphics is.

    – The aircrash map that I discuss above won a newspaper visualization contest. Again, this seems pretty mainstream to me. If it's a straw man, then let's just say that this particular straw man is all over the place and gets a lot of respect!

    – As noted in the linked blog entry, I was invited to speak at Vis Week but they didn't want me to do a remote presentation. I wish I'd been able to do so, so as to communicate with those people directly (rather than through this blog).

    – Finally, and most importantly, my goal was not to criticize visualizations (although I can see how my blog and my talk could give that impression). My goal was to highlight the differences between the infovis and statgraphics perspectives, in order to better understand the different goals being pursued by these different groups of people. I'd love to work with you and others to more carefully explore what these implicit and explicit goals are.