Visualizing uncertainty in data with adaptive jk-plots
Adaptive Uncertainty Visualization With jk-Plots
Human-Computer Interaction
Summary
When we estimate things from data, we often want to understand how certain or uncertain those estimates are, especially when the amount of data changes. The authors propose a new way to show this uncertainty using jk-plots, which adaptively highlight how the number of observations affects precision. These plots combine examples of likely models with the actual data to make uncertainty clearer. They created software in R to generate these visuals and showed how they work on example data sets.
What this means in practice
- •For data analysts: Produce clear visual summaries that show how data amount affects estimate certainty, improving insight into small or large datasets.
- •For statistical software developers: Integrate jk-plots into analytic tools to enhance uncertainty visualization by adaptively combining models and data observations.
Authors
Nikolaus Piccolotto, Daniel Pahr, Laura Lotteraner, Fatih Öztank, Markus Bögl
Abstract
An important task of uncertainty visualizations is to communicate how the number of available observations influences the precision of estimates, such as a Normal distribution's mean. In this paper, we propose an adaptive approach to visualizing univariate data that produces salient representations while highlighting the uncertainty introduced by the sample size. We introduce jk-plots, inspired by educational material of Bayesian statistics, that combine visualizations of plausible reference models (emulating popular uncertainty visualization idioms) and the observations. We describe a visualization pipeline to create jk-plots, which we implemented in an R package. We demonstrate jk-plots using synthetic datasets of varying size and discuss possible usage scenarios in domain expert interviews.