A0405
Title: The hidden algebra of interactive visualization: Exploring the links between graphics, statistics, and interaction
Authors: Adam Bartonicek - The University of Auckland (New Zealand) [presenting]
Abstract: With the rise of web technologies, interactive data visualizations have become a staple of data presentation. Yet, despite the growing popularity of interactive graphics, a formal framework is still lacking for turning raw data into statistical summaries that can be interactively visualized. The reason for this lack may be a subtle yet profound issue: while it is often desirable to treat the statistical summaries and geometric objects in the plots as independent components, this is rarely the case. Consider an ordinary stacked barplot. Data visualization researchers have long warned that while stacking some statistics, such as counts or sums, will produce a valid overall statistic, stacking others will not. But what are the mathematical properties that make this possible? Can other summaries be stacked? And why do stacked plots, despite general reluctance in static visualization, still enjoy wide popularity in interactive visualization? The purpose is to delve into the relationship between graphics, statistics and interaction. Specifically, by discussing various concepts from category theory, such as monoids and groups, the hope is to provide a new appreciation of the rich structure that lies beyond the figures observed daily. Finally, a new R package, plotscaper, is briefly introduced for interactive data exploration, which is an attempt to implement some of these ideas.
