When the average lies
Ten people in a bar. A billionaire walks in. Now the average person is a millionaire.
The idea
The mean is pulled by extreme values; the median isn’t. On skewed data like income, house prices or response times, the mean can describe almost nobody.
This lesson explores a skewed dataset the way an analyst would: summary statistics, a histogram, percentiles, and a decision about which number to report.
What the lesson will build
- A skewed dataset with one extreme value
- Mean, median and percentiles before and after the outlier
- A histogram that shows why the two disagree
Key ideas
- Skew
- Outliers
- Percentiles (p50, p95, p99)
- Choosing the right summary
The video
- Long form: A row of people with the average marker sliding far to the right when one extreme value arrives, while the median barely moves.
- Short: The average moved a mile. The median didn’t.
When it’s published, the code will live in exploratory-data-analysis/ and this page will link to it.