The ladder of abstraction in statistical graphics

It was so much fun having a graphics post yesterday that I thought I’d do another, this time sharing one of my favorite recent articles, which begins:

Graphical forms such as scatterplots, line plots, and histograms are so familiar that it can be easy to forget how abstract they are. As a result, we often produce graphs that are difficult to follow. We propose a strategy for graphical communication by climbing a ladder of abstraction, starting with simple plots of special cases and then at each step embedding a graph into a more general framework. We demonstrate with two examples, first graphing a set of equations related to a modeled trajectory and then graphing data from an analysis of income and voting.

I really like this idea of presenting a sequence of increasingly abstract graphs. It’s kind of a graphical analogue to statistical workflow, in that we can understand the more complicated product by explicitly connecting it to the simpler steps that came before. All too often, we have this killer graph which we then have to spend lots of time explaining. Instead of presenting the graph and providing a separate explanation, my new recommendation is to build up from simpler graphs, explaining each new degree of freedom as it comes up.