New Scatterplot Designs and Graph Perception

What is it about?

Changing the sizes and opacities of points in scatterplots can change how we perceive them. Correlation, or the level of relatedness between two variables, is consistently underestimated when presented using scatterplots. In this work we present alternative scatterplot designs in an attempt to address this bias, and show that there is a great deal of scope for using visual features to change perceptions.

Featured Image

Photo by Carlos Muza on Unsplash

Photo by Carlos Muza on Unsplash

Why is it important?

Scatterplots are used everywhere, including in health communication and as evidence in court cases. Our current usage of these plots assumes that people interpret them accurately, but we know from research that this is not necessarily the case. In this work we offer designers new ways to design scatterplots that may be understood better by the general public.