Principles of Data Visualization. Jeffrey University of Washington

Transcription

1 Principles of Data Visualization Jeffrey University of Washington

2 Data Analysis & Statistics, Tukey & Wilk 1966

3 Four major influences act on data analysis today: 1. The formal theories of statistics. 2. Accelerating developments in computers and display devices. 3. The challenge, in many fields, of more and larger bodies of data. 4. The emphasis on quantification in a wider variety of disciplines. Data Analysis & Statistics, Tukey & Wilk 1966

4 While some of the influences of statistical theory on data analysis have been helpful, others have not. Data Analysis & Statistics, Tukey & Wilk 1966

5 Exposure, the effective laying open of the data to display the unanticipated, is to us a major portion of data analysis It is not clear how the informality and flexibility appropriate to the exploratory character of exposure can be fitted into any of the structures of formal statistics so far proposed. Data Analysis & Statistics, Tukey & Wilk 1966

6 Set A Set B Set C Set D X Y X Y X Y X Y Summary Statistics Linear Regression u X = 9.0 σ X = Y 2 = X u Y = 7.5 σ Y = 2.03 R 2 = 0.67 Anscombe 1973

7 Set A Set B Y Set C Set D Y X X

8

9

10

11 Wikipedia History Flow [Viégas & Wattenberg 04]

12

13

14 d3.js Data-Driven Documents with Mike Bostock, Vadim Ogievetsky [InfoVis 11]

15

16 d3 d3

17 What makes a visualization good?

18 Design Principles [Mackinlay 86] Expressiveness A set of facts is expressible in a visual language if the sentences (i.e. the visualizations) in the language express all the facts in the set of data, and only the facts in the data. Effectiveness A visualization is more effective than another visualization if the information conveyed by one visualization is more readily perceived than the information in the other visualization.

19 Design Principles [Mackinlay 86] Expressiveness A set of facts is expressible in a visual language if the sentences (i.e. the visualizations) in the language express all the facts in the set of data, and only the facts in the data. Effectiveness A visualization is more effective than another visualization if the information conveyed by one visualization is more readily perceived than the information in the other visualization.

20 Expresses Facts Not in the Data A length is interpreted as a quantitative value.

21 Design Principles [Mackinlay 86] Expressiveness A set of facts is expressible in a visual language if the sentences (i.e. the visualizations) in the language express all the facts in the set of data, and only the facts in the data. Effectiveness A visualization is more effective than another visualization if the information conveyed by one visualization is more readily perceived than the information in the other visualization.

22 Design Principles [Mackinlay 86] Expressiveness A set of facts is expressible in a visual language if the sentences (i.e. the visualizations) in the language express all the facts in the set of data, and only the facts in the data. Effectiveness A visualization is more effective than another visualization if the information conveyed by one visualization is more readily perceived than the information in the other visualization.

23 Design Principles [Tversky 02] Congruence The structure and content of the external representation should correspond to the desired structure and content of the internal representation. Apprehension The structure and content of the external representation should be readily and accurately perceived and comprehended.

24 Design Principles Translated Tell the truth and nothing but the truth (don t lie, and don t lie by omission) Use encodings that people decode better (where better = more accurate and/or faster)

25 A quick experiment

26 Compare area of circles

27 Compare length of bars

28 Steven s Power Law Exponent (Empirically Determined) Perceived Sensation Physical Intensity Graph from Wilkinson 99, based on Stevens 61

29 Graphical Perception [Cleveland & McGill 84]

30 Position 1 Position 2 Position 3 Length 1 Length 2 Angle Area (Circular) Area (Rect 1) Area (Rect 2) Log Absolute Estimation Error Graphical Perception Experiments Empirical estimates of encoding effectiveness

31 Comparing Two Quantities Most accurate Position (common) scale Position (non-aligned) scale Length Slope Angle Area Volume Least accurate Color hue-saturation-density

32 Effectiveness Rankings [Mackinlay 86] QUANTITATIVE ORDINAL NOMINAL Position Position Position Length Density (Value) Color Hue Angle Color Sat Texture Slope Color Hue Connection Area (Size) Texture Containment Volume Connection Density (Value) Density (Value) Containment Color Sat Color Sat Length Shape Color Hue Angle Length Texture Slope Angle Connection Area (Size) Slope Containment Volume Area Shape Shape Volume

33 Effectiveness Rankings [Mackinlay 86] QUANTITATIVE ORDINAL NOMINAL Position Position Position Length Density (Value) Color Hue Angle Color Sat Texture Slope Color Hue Connection Area (Size) Texture Containment Volume Connection Density (Value) Density (Value) Containment Color Sat Color Sat Length Shape Color Hue Angle Length Texture Slope Angle Connection Area (Size) Slope Containment Volume Area Shape Shape Volume

34 Effectiveness Rankings [Mackinlay 86] QUANTITATIVE ORDINAL NOMINAL Position Position Position Length Density (Value) Color Hue Angle Color Sat Texture Slope Color Hue Connection Area (Size) Texture Containment Volume Connection Density (Value) Density (Value) Containment Color Sat Color Sat Length Shape Color Hue Angle Length Texture Slope Angle Connection Area (Size) Slope Containment Volume Area Shape Shape Volume

35 Gene Expression Time-Series [Meyer et al 11] Color Encoding Position Encoding

36 Artery Visualization [Borkin et al 11] Rainbow Palette Diverging Palette 62% 92% 2D 39% 71% 3D

37 Additional Resources The Visual Display of Quantitative Information. Edward Tufte. Show Me the Numbers. Stephen Few. Visualizing Data. William S. Cleveland. Perception for Design. Colin Ware.

38 Principles of Data Visualization Jeffrey