The Datasaurus Dozen

An illustrative exercise in never trusting the summary statistics without also visualizing them.

Usage

Datasaurus

Format

A data frame with 1,846 observations on the following 3 variables.

dataset

the particular data set, one of 12

x

a random variable

y

another random variable

Details

Data were created by Alberto Cairo to illustrate you should always visualize your data beyond the summary statistics. These are 12 data sets, in long form, each with a mean of x about 54.26, a mean of y about 47.83. The standard deviation for x is about 16.76 and the standard deviation of y is about 26.93. x and y will correlate weakly, about -.06.

References

Matejka, Justin and George Fitzmaurice. 2017. “Same Stats, Different Graphs: Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing.” ACM SIGCHI Conference on Human Factors in Computing Systems.

Author

Alberto Cairo, Justin Matejka, George Fitzmaurice