Why scatter plots suggest causality, and what we can do about it
This tackles the issue of misleading causal inferences in data visualization for scientists and the general public, offering a novel solution to improve interpretation accuracy.
The paper addresses the problem that scatter plots implicitly suggest causality by convention, which can mislead both public and professional interpretations of data. They propose a new visualization called diamond plots, which rotate scatter plots by 45 degrees to indicate a purely correlative relationship.
Scatter plots carry an implicit if subtle message about causality. Whether we look at functions of one variable in pure mathematics, plots of experimental measurements as a function of the experimental conditions, or scatter plots of predictor and response variables, the value plotted on the vertical axis is by convention assumed to be determined or influenced by the value on the horizontal axis. This is a problem for the public understanding of scientific results and perhaps also for professional scientists' interpretations of scatter plots. To avoid suggesting a causal relationship between the x and y values in a scatter plot, we propose a new type of data visualization, the diamond plot. Diamond plots are essentially 45 degree rotations of ordinary scatter plots; by visually jarring the viewer they clearly indicate that she should not draw the usual distinction between independent/predictor variable and dependent/response variable. Instead, she should see the relationship as purely correlative.