In the first module you learned to describe a distribution by looking at it. Now you will learn to summarize it — to compress a whole column of numbers into a few that capture its center and its spread. These are the numbers that fill every report and headline: the average price, the typical commute, the standard margin of error.

You will start with the three measures of center — the mean, the median, and the mode — and learn the one that beginners overlook: each answers a slightly different question, and the right choice depends on the shape of your data. Then you will move to spread, because a center alone can lie. Two datasets with the same average can be worlds apart in how tightly their values cluster, and range, variance, and standard deviation are how you measure that. You will finish with the z-score, the simple idea that lets you compare values measured on completely different scales.

Every lesson uses one real dataset: the technical specs of 398 cars from the 1970s and early 80s — their fuel economy, weight, horsepower, and origin. By the end you will know not just how to compute an average, but when an average is the wrong number to report.

Start with Lesson 1 and the most familiar statistic of all — the mean — and the surprising amount it hides.