[Video] Data Visualization, Neuroscience, and Why It Matters to the Analyst

Data visualization (and data storytelling) are critical skills for the analyst to develop. I’ve lost count of how many times I’ve presented on the subject. This presentation at Superweek in early 2020 (late January… just before the world shut down due to COVID) wound up getting expanded to the point of being a multi-hour online course through CXL by that fall.

In this presentation, I stood on the shoulders of Stephen Few, Edward Tufte, Cole Nussbaumer Knaflic, and Lea Pica to explain what I think are some of the most critical concepts and techniques when it comes to data visualization (I did not get into data storytelling):

• The three types of memory: iconic (visual sensory register), short-term, and long term
• Miller’s Law (7±2 and short-term memory)
• What cognitive load is (including demonstrating it with several examples)
• Gestalt principles–not because they need to be overtly learned and applied, but as an illustration of how subtle changes to a visualization can drastically change how we perceive a visual
• My favorite data visualization tip: maximizing the data-pixel ratio (including applying the concept to both charts and tables)
• Why pie charts (and doughnut charts) are (generally speaking) evil–illustrated by assessing them through a cognitive load lens
• Why horizontal bar charts, conversely, are often pretty awesome
• A quick review of some non-standard data visualizations that can be very effective: slopegraphs, heatmap tables, scatterplots, and network diagrams