Monday, August 29, 2016

Download the Datasaurus: Never trust summary statistics alone; always visualize your data

This tweet is quickly becoming the most popular I've ever written. I drew that dinosaur with this fantastic tool created by Robert Grant, a statistician and visualization designer. It lets you plot any points on a scatter plot and then download the corresponding data.

In case you want to use the Datasaurus in your classes or talks to illustrate how important it is to visualize data while analyzing it, feel free to download the data set from this Dropbox link.* It'll be fun to first show your audience just the figures and the summary statistics, and then ask them to make the chart:


Update: Maarten Lambrechts proposes to call this the Anscombosaurus, honoring Francis Anscombe's quartet. I like it.

*NOTE: You can use the data and illustrations for any other purpose. They aren't copyrighted.