Boston Data Swap: Data Vis Under Uncertainty

Visual methods for dealing with uncertainty. Notes and links for presentation: https://gist.github.com/Protonk/4961378

Transcript

1. Data Visualization
 Under Uncertainty" Adam Hyland, Engineer at Bocoup"
2. Love Means Never Having to Say You’re Sorry"
3. Goals" • Develop a narrative" • Expose a civic issue" • Make clear a message"
4. Stakes" • Visuals are powerful" • Civic data can expose hard questions"
6. Certainty and Narrative" The...decision we made was to present data that fell within documented ranges, rather than reflect the findings of a particular report, because of the inherent challenge in collecting data on this issue. -Sarah Beaulieu, Enliven
7. What happened?" • Enliven presented a point estimate! • They felt this was a responsible choice" • Actual data is animated by uncertainty"
8. How do we do it now?" • Where do we handle uncertainty in visualization well?" • Sciences" • Forecasting" • Poorly?" • Pretty much everywhere else"
9. But sometimes..."
10. Taxonomy" • Stochastic uncertainty " • Model uncertainty (error)"
11. But I repeat myself" • What do we mean by stochastic uncertainty?" • Dispersion" • Sampled or not"
12. Polls" • Not a strawman" • Standard presentation" • Cognitive load"
13. It gets better"
14. What`s better, exactly?" • The Good:" • Conveys dispersion in results" • Helps reader to infer estimate " • The Bad:" • Let`s see the site itself..." • The Ugly:" • Overplotting, etc."
15. Visual language" • How do we think about stochastic uncertainty?" • How to show it?" • Boxplots" • Density estimates" • Bootstrap" • Models: in our department?"
16. Boxplot"
17. What is a boxplot?"
18. Density Estimates"
19. Think back to Pollster"
20. Model Uncertainty" • Model error is a term of art" • Can refer to errors in statistical models, or simpler models"
21. Analytics"
22. Messy data"
24. Let`s do it!" • Push new things into our visual language" • People trained by bad visualization" • Retraining is hard work"
25. Implementation" • R" • ggplot2" • MASS, base distributions" • JavaScript" • d3 (d3.chart!)" • Lots of cool stuff here"
26. That was fun,
 right?"