Infovis vs. statgraphics: A clear example of their different goals

Posted on by

I recently came across a data visualization that perfectly demonstrates the difference between the “infovis” and “statgraphics” perspectives.

Here’s the image (link from Tyler Cowen):

That’s the infovis. The statgraphic version would simply be a dotplot, something like this:

(I purposely used the default settings in R with only minor modifications here to demonstrate what happens if you just want to plot the data with minimal effort.)

Let’s compare the two graphs:

From a statistical graphics perspective, the second graph dominates. The countries are directly comparable and the numbers are indicated by positions rather than area. The first graph is full of distracting color and gives the misleading visual impression that the total GDP of countries 5-10 is about equal to that of countries 1-4.

If the goal is to get attention, though, it’s another story. There’s nothing special about the top graph above except how it looks. It represents neither a data-gathering effort, nor a statistical analysis, nor even a clever juxtaposition (as in the famous graph of health costs and life expectancies). If someone had posted the second graph above (the lineplot), I doubt it would’ve been sent around the web, and I doubt that Cowen would’ve noticed it in the first place.

Thus, in this modern world of multichannel communications, chartjunk does have a purpose: it gets you noticed.

P.S. Here’s my R code:

png ("africagdp.png", height=350, width=400)
countries <- c ("South Africa", "Egypt", "Nigeria", "Algeria",
"Morocco", "Angola", "Libya", "Tunisia", "Kenya", "Ethiopia",
"Ghana", "Cameroon")
gdp <- c (285.4, 188.4, 173, 140.6, 91.4, 75.5, 62.3,
39.6, 29.4, 28.5, 26.2, 22.2)
dotchart (rev(gdp), rev(countries),
xlab="GDP in billions of US dollars",
main="African Countries by GDP",
xlim=max(gdp)*c(.038,1.02), pch=20)
dev.off ()

8 thoughts on “Infovis vs. statgraphics: A clear example of their different goals”

  3. One point immediately strikes me though in the first viz. I can visually fit the smaller squares inside the larger squares and make statements like "GDP for South Africa is more than Morocco, Angola, Libya and Tunisia combined". This immediate comparison was not triggered in the second graphic. An interactive graphic where the squares can be moved on top of each other to see coverage could have been nice too. The same comparisons can be done in my head (by making the additions) or on a separate sheet of paper but I am not sure which one I would have picked since I would have done it anyways.

    • William:

      Your comparison could be incorporated into the second graph by adding a line such as "Kenya, Ethiopia, Ghana, and Cameroon together." Maybe it would also be a good idea to add a line, something like, "All other 45 African countries combined."

  4. I don't really agree that there is a difference between an "infographic" and a "statgraphic" as you outlined here. The major difference between these two graphics is that for the first, data is represented by an area and in the second it is represented by a length. Although the second makes comparison across countries easier, the effectiveness of communicating is subject to debate and the intentions of the author. The first likely does a better job of communicating how much of Africa's total GDP comes from South Africa (as in pie charts or tree maps). Whether the first one does a better job at grabbing the users attention through a broad spectrum of rainbow colors (hurts my eyes) or the second one cannot be improved upon with the use of a better labeling or additional color scheme is open to debate.

    • Michael:

      The top graph does not tell you how much of Africa's total GDP comes from South Africa. It only shows the top 10. It would be easy enough to show the total on either graph, though. In my graph you could show the total by extending the x-axis to the right and putting a vertical dotted line where the total is, along with vertical dotted lines at 25%, 50%, and 75% of the total.

  5. Pingback: Using a “pure infographic” to explore differences between information visualization and statistical graphics « Statistical Modeling, Causal Inference, and Social Science

Comments are closed.