Tufte
Visual Display of Quantitative Information

Tufte defines visualization: "data graphics visually display measured quantities by means of the combined use of points, lines, a coordinate system, numbers, symbols, words, shading, and color. " p. 9

"statistical graphics -- length and area to show quantity, time-series, scatterplots, and multivariate displays" p. 9

**"at their best, graphics are instruments for reasoning about quantitative information.  Often the most effective way to describe, explore, and summarize a set of numbers -- even a very large set -- is to look at pictures of those numbers." p. 9

In this book, emphasis on [1] maximizing principles, [2] empirical measures of graphical performance, and [3] the sequential improvement of graphics through revision and editing
"Insights are to be gained, I believe, from theories of what makes for excellence in art, architecture, and prose." p. 9

Tufte's rules:
"Graphical displays should:
         - show the data
         - induce the viewer to think about the substance rather than about methodology, graphic design, the technology of graphic production, or something else
         - avoid distorting what the data have to say
         - present many numbers in a small space
         - make large data sets coherent
         - encourage the eye to compare different pieces of data
         - reveal the data at several levels of detail, from a broad overview to the fine structure
         - serve a reasonably clear purpose: description, exploration, tabulation, or decoration
         - be closely integrated with the statistical and verbal descriptions of a data set

[1] Principles of Graphical Excellence
         - Graphical excellence is the well-designed presentation of interesting data -- a matter of substance, of statistics, and of design
         - Graphical excellence consists of complex ideas communicated with clarity, precision, and efficiency.
         - Graphical excellence is that which gives to the viewer the greatest number of ideas in the shortest time with the least ink in the smallest space
         - Graphical excellence is nearly always multivariate
         - And graphical excellence requires telling the truth about the data.

Preoccupations that keep us from taking graphics seriously:
         - assumption that it is easy to lie
         - assumption "that data graphics were mainly devices for showing the obvious to the ignorant"

John Tukey's work in 1970-72  -- "graphics were used as instruments for reasoning about quantitative information" p. 53.

Graphical Integrity
         - The representation of numbers, as physically measured on the surface of the graphic itself, should be directly proportional to the numerical quantities represented.
         - Clear, detailed, and thorough labeling should be used to defeat graphical distortion and ambiguity.  Write out explanations of the data on the graphic itself.  Label important events in the data.
         - Show data variation, not design variation.
         - In time-series displays of money, deflated and standardized units of monetary measurement are nearly always better than nominal units.
         - The number of information-carrying (variable) dimensions depicted should not exceed the number of dimensions in the data
         - Graphics must not quote data out of context.

"Five principles in the theroy of data graphics produce substantial changes in graphical design. .."
         - Above all else show the data
         - Maximize the data-ink ratio
         - Erase non-data-ink
         - Erase redundant data-ink
         - Revise and edit" p. 105

Chapter 5: Chartjunk: Vibrations, Grids, and Ducks

         - Forgo chartjunk including: moire vibration, the grid, and the duck

Chapter 6: Data-Ink Maximization and Graphical Design
Chapter 7: Multifunctioning Graphical Elements
Chapter 8: Data Density and Small Multiples

"Well-designed small multiples are
         - inevitably comparative
         - deftly multivariate
         - shrunken, high-density graphics
         - usually based on a large data matrix
         - drawn almost entirely with data-ink
         - efficient in interpretation
         - often narrative in content, showing shifts in the relationship between variables as the index variable changes (thereby revealing interaction or multiplicative effects).

Small multiples reflect much of the theory of data graphics:
         - For non-data-ink, less is more
         - For data-ink, less is a bore

Chapter 9: Aesthetics and Technique in Data Graphical Design

         - "Graphical elegance is often found in simplicity of design and complexity of data" p. 177

"...some guides for enhancing the visual quality of routine, workaday designs.  Attractive displays of statistical information
         - have a properly chosen format and design
         - use words, numbers, and drawing together
         - reflect a balance, a proportion, a sense of relevant scale
         - display an accessible complexity of detail
         - often have a narrative quality, a story to tell about the data
         - are drawn in a professional manner, with the technical details of production done with care
         - avoid content-free decoration, including chartjunk