|Title: The Elements of Graphing Data 2nd ed|
Authors: William S. Cleveland
Publishers: Hobart Press
Publication Date: 1994-10-01
graphs of different aspect ratio can give different information.
The same data can look very different in a line chart depending on its aspect ratio.
A change in aspect ratio means a change in the angle of the lines
Example: sunspot vs year
In a paper from 1988, Bill Cleveland, Marylyn McGill, and Robert McGill proposed the idea that the average line slope in a line chart should be 45º. This has been dubbed banking to 45º and has turned into one of the bits of common wisdom in visualization as determining the ideal aspect ratio.
if the goal is to be able to compare the rates of change between lines, the 45º average slope makes sense as a rule
after this paper: http://vis.stanford.edu/papers/slope-ratio-comparison
calculate optimal aspect ratio: http://vis.berkeley.edu/papers/banking/
June 3, 2013 at 9:08 pm
over the years, i have noted that actual EXPERIMENTS on graphs – asking people to react to diff graphs –
have in fact been done, but the literature is so scattered, in so many diff silos, that no one seems to know much
eg, there is a lady in MI, a medical information type, who has done studies on how tables of clinical data affect how people respond to tests results
be nice if some PhD student took the time to put it all together.
I think I’ve lost most of the links I’ve gathered (there was a review in Science (AAAS) last year or so