Simply Statistics A statistics blog by Rafa Irizarry, Roger Peng, and Jeff Leek

How do I know if my figure is too complicated?

One of the key things every statistician needs to learn is how to create informative figures and graphs. Sometimes, it is easy to use off-the-shelf plots like barplots, histograms, or if one is truly desperate a pie-chart

But sometimes the information you are trying to communicate requires the development of a new graphic. I am currently working on a project with a graduate student where the standard illustration are Venn Diagrams - including complicated Venn Diagrams with 5 or 10 circles. 

As we were thinking about different ways of illustrating our data, I started thinking about what are the key qualities of a graphic and how do I know if it is too complicated. I realized that:

  1. Ideally just looking at the graphic one can intuitively understand what is going on, but sometimes for more technical/involved displays this isn’t possible
  2. Alternatively, I think a good plot should be able to be explained in 2 sentences or less. I think that is true for pretty much every plot I use regularly. 
  3. That isn’t including describing what different colors/sizes/shapes specifically represent in any particular version of the graphic. 

I feel like there is probably something to this in the Grammar of Graphics or in some of William Cleveland’s work. But this is one of the first times I’ve come up with a case where a new, generalizable, type of graph needs to be developed.