The Green Lab - [11-A] Data Visualization
1 like1,733 views
The document discusses data visualization, describing it as the use of interactive visual representations to enhance understanding of abstract data. It covers key principles such as graphical integrity, proportionality, utility, and clarity, alongside techniques for encoding both quantitative and categorical information. The material concludes with references for further reading and a reminder for an upcoming ggplot tutorial session.
![Vrije Universiteit Amsterdam
13 Giuseppe Procaccianti / S2 group / The Green Lab
Graphical integrity [1]
● Data visualization must tell the truth
[1] Edward R. Tufte, 1983. The Visual Display of Quantitative Information. Graphics Press.
● Avoid misleading information and chartjunk](https://image.slidesharecdn.com/11-adatavisualization-161031134602/85/The-Green-Lab-11-A-Data-Visualization-13-320.jpg)
The Green Lab - [11-A] Data Visualization
- 1. 1 Het begint met een idee Data Visualization Giuseppe Procaccianti
- 2. Vrije Universiteit Amsterdam 2 Giuseppe Procaccianti / S2 group / The Green Lab Quick Recap: Experimental Process Experiment scoping Experiment planning Idea Experiment operation Analysis & interpretation Presentation & package
- 3. Vrije Universiteit Amsterdam 3 Giuseppe Procaccianti / S2 group / The Green Lab What is Data Visualization? «The use of computer-supported, interactive, visual representations of abstract data to amplify cognition». Readings in Information Visualization: Using Vision to Think. S.K.Card, J.D.Mackinlay, and B.Shneiderman, Academic Press, 1999
- 4. Vrije Universiteit Amsterdam 4 Giuseppe Procaccianti / S2 group / The Green Lab Examples of amplified cognition
- 5. Vrije Universiteit Amsterdam 5 Giuseppe Procaccianti / S2 group / The Green Lab More examples of amplified cognition WTF Visualizations: http://viz.wtf/
- 6. Vrije Universiteit Amsterdam 6 Giuseppe Procaccianti / S2 group / The Green Lab Data visualization: science or art?
- 7. Vrije Universiteit Amsterdam 7 Giuseppe Procaccianti / S2 group / The Green Lab Data visualization theory Quantitative communication
- 8. Vrije Universiteit Amsterdam 8 Giuseppe Procaccianti / S2 group / The Green Lab Quantitative communication Quantitative values (measures) Categorical information (groups)
- 9. Vrije Universiteit Amsterdam 9 Giuseppe Procaccianti / S2 group / The Green Lab Quantitative communication: example Categorical information (name) Categorical information (group) Quantitative values
- 10. Vrije Universiteit Amsterdam 10 Giuseppe Procaccianti / S2 group / The Green Lab Quantitative communication: example Both Categorical Quantitative
- 11. Vrije Universiteit Amsterdam 11 Giuseppe Procaccianti / S2 group / The Green Lab Tables vs. graphs Tables ● Easy look-up of values (comparisons) ● Precise values ● Different units of measure are possible Graphs ● Overall "shape" of data (trends) ● Reveal relationships between multiple variables
- 12. Vrije Universiteit Amsterdam 12 Giuseppe Procaccianti / S2 group / The Green Lab Data visualization theory Graphical Integrity
- 13. Vrije Universiteit Amsterdam 13 Giuseppe Procaccianti / S2 group / The Green Lab Graphical integrity [1] ● Data visualization must tell the truth [1] Edward R. Tufte, 1983. The Visual Display of Quantitative Information. Graphics Press. ● Avoid misleading information and chartjunk
- 14. Vrije Universiteit Amsterdam 14 Giuseppe Procaccianti / S2 group / The Green Lab Graphical integrity: principles ● Proportionality ● Utility ● Clarity
- 15. Vrije Universiteit Amsterdam 15 Giuseppe Procaccianti / S2 group / The Green Lab Proportionality: Lie Factor ● Ideal LF = 1 ○ if LF > 1 you are overstating an effect ○ if LF < 1 you are understating an effect
- 16. Vrije Universiteit Amsterdam 16 Giuseppe Procaccianti / S2 group / The Green Lab Proportionality: Lie Factor Data Visualization 5.3/0.6 = 8.83 27.5/18 = 1.53 LF=5.77
- 17. Vrije Universiteit Amsterdam 17 Giuseppe Procaccianti / S2 group / The Green Lab Utility: data ink ● Ideal Data-Ink ratio != 1 ○ a balance must be found between readability and utility
- 18. Vrije Universiteit Amsterdam 18 Giuseppe Procaccianti / S2 group / The Green Lab Utility: data ink
- 19. Vrije Universiteit Amsterdam 19 Giuseppe Procaccianti / S2 group / The Green Lab Utility: data ink
- 20. Vrije Universiteit Amsterdam 20 Giuseppe Procaccianti / S2 group / The Green Lab Clarity
- 21. Vrije Universiteit Amsterdam 21 Giuseppe Procaccianti / S2 group / The Green Lab Clarity
- 22. Vrije Universiteit Amsterdam 22 Giuseppe Procaccianti / S2 group / The Green Lab Data visualization theory Information Encoding
- 23. Vrije Universiteit Amsterdam 23 Giuseppe Procaccianti / S2 group / The Green Lab How to encode information in a graph ● Quantitative information ○ Points: relative position ○ Lines: relative position, slope, length ○ Bars: length (height) ○ (2D) shapes: area
- 24. Vrije Universiteit Amsterdam 24 Giuseppe Procaccianti / S2 group / The Green Lab Points
- 25. Vrije Universiteit Amsterdam 25 Giuseppe Procaccianti / S2 group / The Green Lab Lines
- 26. Vrije Universiteit Amsterdam 26 Giuseppe Procaccianti / S2 group / The Green Lab Lines
- 27. Vrije Universiteit Amsterdam 27 Giuseppe Procaccianti / S2 group / The Green Lab Bars Width plays no role! Zero-based scale (LF)
- 28. Vrije Universiteit Amsterdam 28 Giuseppe Procaccianti / S2 group / The Green Lab Columns
- 29. Vrije Universiteit Amsterdam 29 Giuseppe Procaccianti / S2 group / The Green Lab 2D shapes (the infamous pie chart) Always put percentages!
- 30. Vrije Universiteit Amsterdam 30 Giuseppe Procaccianti / S2 group / The Green Lab 2D shapes (the infamous pie chart)
- 31. Vrije Universiteit Amsterdam 31 Giuseppe Procaccianti / S2 group / The Green Lab How to encode information in a graph ● Categorical information ○ Position (along an axis) ○ Color ○ Shape ○ Fill ○ Linestyle
- 32. Vrije Universiteit Amsterdam 32 Giuseppe Procaccianti / S2 group / The Green Lab Position, color
- 33. Vrije Universiteit Amsterdam 33 Giuseppe Procaccianti / S2 group / The Green Lab Shape
- 34. Vrije Universiteit Amsterdam 34 Giuseppe Procaccianti / S2 group / The Green Lab Next lab session: ggplot tutorial ● R advanced graphics package ● https://cran.r-project.org/web/packages/ggplot2/index.html ● REMINDER: Wednesday 9am!!
- 35. Vrije Universiteit Amsterdam 35 Giuseppe Procaccianti / S2 group / The Green Lab References and further readings ● Graph design principles, M. Torchiano (slides) on BB ● Edward R. Tufte, 1983. The Visual Display of Quantitative Information. Graphics Press. ● Manuel Lima: A visual history of human knowledge
- 36. Vrije Universiteit Amsterdam 36 Giuseppe Procaccianti / S2 group / The Green Lab Thank you! g.procaccianti@vu.nl i.malavolta@vu.nl