Edward R. Tufte and the Design of Statistical Graphics

Edward Rolf Tufte, born 1942, is an American statistician and professor emeritus of political science, statistics, and computer science at Yale University. Whilst teaching a statistics class in 1975, Tufte devised a set of readings and lectures on statistical graphics, producing visual graphics to help explain or demonstrate quantity, time passing, density etc.

Modern data graphics are now often used instead of statistical tables, as looking at visual images can be the most effective way to describe, explore and summarize these numbers.

For example:

This table of statistics would mean little to most people, however when it is translated into a visual graphic, it is made vividly clear how the statistics differ:

Tufte went on to compile many books on statistical graphics, charts and tables, filled with illustrations of the best (and a few of the worst) statistical graphics, with detailed analysis of how to display data for precise, effective, quick analysis. He explored the importance and effectiveness of various types of statistical graphics, such as scatterplots, time-series graphs, data maps, and other types of visual data that we are presented with almost everyday to help make statistical information more accessible.

This visual data can be graphical and mathematical like the graph seen above, or it could be purely image based, for example these images by E.J. Marey (1830-1904) depicting the movement of certain animals.

Tufte also coined two phrases often used to describe the visual communication of information:

"Chartjunk", to describe useless, non-informative or distracting elements of quantitative information displays.

"Data-ink Ratio", to condemn excessive decoration of visual quantitative information. Tufte believed that data graphics should draw the viewer's attention to the sense and substance of the data, not to something else. The majority of the ink on a graphic should present data-information, and not be used for decorative and consequently distracting graphics, such as the graph to the left.