The overall pattern of where values land — which values occur, and how often each one does.
Visual intuition
30
31
32
33
most values
mean pulled right
300
One extreme value can drag summaries away from the cluster
A distribution is the whole shape of the data: the tight cluster and the far-out straggler both belong to it.
Example
In an illustrative town, most commutes cluster around 20-30 minutes while a few exceed 90 — a right-skewed distribution, so the commute is longer than the typical one.
How It Works
Write down every commute in town: lots near 25 minutes, fewer near 50, a stubborn few past 90. That whole pattern — the pile-up, the spread, the tail — is the distribution. Summary numbers like the compress it to a single point, and two very different distributions can share the same mean, which is why looking at the shape often changes the conclusion.