Foundations & the Data-Science Workflow

Summary Statistics

Summary statistics are single numbers that capture some essential feature of a whole batch of data, so you can grasp it without reading every value. They fall mainly into measures of centre (where the values cluster, like the mean or median) and measures of spread (how scattered they are, like the range or standard deviation).

A good summary saves time, but every summary also throws information away, and a single number can hide a lot. Two cities can share the same average income while one has a comfortable middle class and the other a handful of billionaires among the poor. The remedy is to report centre and spread together, and to keep a picture of the full distribution nearby.

Also called
descriptive measures