Same Stats, Different Graphs by Autodesk Research

Datasets which have the same statistical properties, yet produce dissimilar graphs, are an effective tool to demonstrate the importance of visualizing your data. Anscombe’s Quartet is the famous example, however, it is not known how Anscobme created his dataset. This work introduces a technique for creating such datasets, including the “Datasaurus Dozen”, which takes the “Datasaurus” dataset from Alberto Cairo, and creates 12 additional datasets each with the same statistical properties.

#