Readings Covered Additional Readings Statistical Graphics - PowerPoint PPT Presentation

Readings Covered Additional Readings Statistical Graphics Multi-Scale Banking to 45 Degrees. Jeffrey Heer, Maneesh Agrawala. Visual information seeking: Tight coupling of dynamic query filters with long history for paper-based views of data IEEE TVCG 12(5) (Proc. InfoVis 2006), Sep/Oct 2006, pages 701-708. starfield displays. Chris Ahlberg and Ben Shneiderman, Proc SIGCHI ’94, springboard for infovis pages 313-317 Lecture 6: Statistical Graphics Animated Transitions in Statistical Data Graphics. Jeffrey Heer and http://www.math.yorku.ca/SCS/Gallery/milestone/ George G. Robertson. IEEE TVCG (Proc. InfoVis 2007) 13(6): Metric-Based Network Exploration and Multiscale Scatterplot. Yves Information Visualization 1240-1247, 2007. Chiricota, Fabien Jourdan, Guy Melancon. Proc. InfoVis 04, pages improving line charts 135-142. CPSC 533C, Fall 2009 Scented Widgets: Improving Navigation Cues with Embedded improving scatterplots Visualizations. Wesley Willett, Jeffrey Heer, and Maneesh Agrawala. The Elements of Graphing Data, William S. Cleveland, Hobart Press interactive dynamic queries IEEE TVCG (Proc InfoVis 2007) 13(6):1129-1136. 1994. Tamara Munzner multiscale structure Graph-Theoretic Scagnostics. Leland Wilkinson, Anushka Anand, and matrix of scatterplots, level of indirection Robert Grossman. Proc InfoVis 05 UBC Computer Science improving statistical graphics animated transitions between graphics Mon, 28 September 2009 making widgets more information-dense 1 / 34 2 / 34 3 / 34 4 / 34 Line Charts Banking to 45 Degrees Multiscale Banking to 45 Choosing Aspect Ratios invented by William Playfair (1759-1823) previous work by Cleveland frequency domain analysis FFT the data, smooth by also bar charts, pie charts, ... find interesting regions at multiple scales convolve with Gaussian perceptual principle: most accurate angle judgement at 45 find interesting degrees spikes/ranges in power spectrum pick line graph aspect ratio (height/width) accordingly cull nearby regions if too similar, ensure overview shown create trend curves for each aspect ratio http://labspace.open.ac.uk/file.php/1872/Mu120 3 021i.jpg http://www.math.yorku.ca/SCS/Gallery/images/playfair-wheat1.gif [www.research.att.com/ ∼ rab/trellis/sunspot.html] [Multi-Scale Banking to 45 Degrees. Heer and Agrawala, Proc InfoVis 2006 vis.berkeley.edu/papers/banking] 5 / 34 6 / 34 7 / 34 8 / 34 Multiscale Banking to 45 Critique Scatterplots Interactive Scatterplots: Dynamic Queries very nice generalization of old idea encode two input variables with spatial position tight coupling: immediate feedback after action does not require interactivity to reap benefits fast, lightweight visual exploration show positive/negative/no correllation between variables vs. composing SQL query [Visual information seeking: Tight coupling of dynamic query filters with starfield [Multi-Scale Banking to 45 Degrees. Heer and Agrawala, Proc InfoVis 2006 displays. Chris Ahlberg and Ben Shneiderman, Proc SIGCHI ’94, p 313-317] [http://upload.wikimedia.org/wikipedia/commons/0/0f/Oldfaithful3.png] [http://www.cs.umd.edu/hcil/pubs/screenshots/FilmFinder/] vis.berkeley.edu/papers/banking] 9 / 34 10 / 34 11 / 34 12 / 34 FilmFinder FilmFinder FilmFinder Multiscale Scatterplots blur shows structure at multiple scales convolve with Gaussian slider to control scale parameter interactively easily selectable regions in quantized image [Metric-Based Network Exploration and Multiscale Scatterplot. Yves Chiricota, Fabien Jourdan, Guy Melancon. Proc. InfoVis 04] 13 / 34 14 / 34 15 / 34 16 / 34 [Visual information seeking: Tight coupling of dynamic query filters with starfield [Visual information seeking: Tight coupling of dynamic query filters with starfield [Visual information seeking: Tight coupling of dynamic query filters with starfield

SPLOM: Scatterplot Matrix Graph-Theoretic Scagnostics Measuring Scatterplots Measuring Scatterplots show all pairwise variable combos side by side reduce problem to constant size aspects and measures overview matrix of 9 geometric metrics outliers: outlying matrix size grows quadratically with variable count meta-SPLOM: each point represents scatterplot shape: convex, skinny, stringy, straight detail on demand to see individual scatterplots computed with convex hull, alpha hull, min span tree trend: monotonic density: skewed, clumpy coherence: striated [Graph-Theoretic Scagnostics. Wilkinson, Anand, and Grossman. Proc InfoVis 05.] [Graph-Theoretic Scagnostics. Wilkinson, Anand, and Grossman. Proc InfoVis 05.] [Graph-Theoretic Scagnostics. Wilkinson, Anand, and Grossman. Proc InfoVis 05.] Graph-Theoretic Scagnostics. Leland Wilkinson, Anushka Anand, and Robert Grossman. Proc InfoVis 05. 17 / 34 18 / 34 19 / 34 20 / 34 Results Results Critique Animated Transitions powerful and elegant method general and powerful idea curse of dimensionality is hard problem transitions, not motion as visual encoding benefits abstraction level clearly appropriate for experts attracts attention unsuitable for novices facilitates object constancy implies causality presentation problem: color use in paper itself emotionally engaging this paper: statistical graphics design principles controlled experiments [Animated Transitions in Statistical Data Graphics. Jeffrey Heer and George G. Robertson. IEEE TVCG (Proc. InfoVis [Graph-Theoretic Scagnostics. Wilkinson, Anand, and Grossman. Proc InfoVis 05.] [Graph-Theoretic Scagnostics. Wilkinson, Anand, and Grossman. Proc InfoVis 05.] 2007) 13(6): 1240-1247, 2007.] 21 / 34 22 / 34 23 / 34 24 / 34 Transition Taxonomy Congruence Principles Apprehension Principles Staging internal and external representations should match change viewpoint external representation structure and content should be both structure and content readily and accurately perceived and comprehended change spatial substrate principles filter principles maintain valid data graphics during transitions reorder group similar transitions use consistent mappings (semantic-syntactic) change time gestalt common fate respect semantic correspondences change visual mapping avoid ambiguity minimize occlusion maximize predictability change data schema slow-in, slow-out use simple transitions use staging for complex transitions make transitions as long as needed, but no longer [Animated Transitions in Statistical Data Graphics. Jeffrey Heer and George G. Robertson. IEEE TVCG (Proc. InfoVis 2007) 13(6): 1240-1247, 2007.] 25 / 34 26 / 34 27 / 34 28 / 34 Experiments Critique Critique Scented Widgets study 1: object location tracking thorough investigation, embedded visualizations for standard UI elements animation always helped goes beyond anecdotal evidence graphically compact/terse staged animation almost always helped information scent cues for navigating info spaces study 2: value change estimation animation helps in some cases staging not significant help preference: staged anim mostly, anim always guideline: avoid overly complex multi-staging [Scented Widgets: Improving Navigation Cues with Embedded Visualizations. Willett, Heer, and Agrawala. IEEE TVCG (Proc InfoVis 2007) 13(6):1129-1136. ] 29 / 34 30 / 34 31 / 34 32 / 34

Implemented Scent Types Example Application Experiments Critique more unique discoveries at first but effect faded over time significant preference no impairment from clutter [Scented Widgets: Improving Navigation Cues with Embedded Visualizations. Willett, [Scented Widgets: Improving Navigation Cues with Embedded Visualizations. Willett, Heer, and Agrawala. IEEE TVCG (Proc InfoVis 2007) 13(6):1129-1136. ] Heer, and Agrawala. IEEE TVCG (Proc InfoVis 2007) 13(6):1129-1136. ] 33 / 34 34 / 34 35 / 34 36 / 34 Critique Reading for Next Time information-dense annotation successful Ware, Chapter 10: Interacting with Visualizations: first half, p 317-324 good discussion of toolkit issues user study solidifies contribution Tufte, Chapter 4: Small Multiples Exploring High-D Spaces with Multiform Matrices and Small Multiples. Alan MacEachren, Xiping Dai, Frank Hardisty, Diansheng Guo, and Gene Lengerich. Proc InfoVis 2003, p 31-38. Building Highly-Coordinated Visualizations In Improvise. Chris Weaver. Proc. InfoVis 2004 The Visual Design and Control of Trellis Display. R. A. Becker, W. S. Cleveland, and M. J. Shyu (1996). Journal of Computational and Statistical Graphics, 5:123-155. 37 / 34 38 / 34