How to Defend Yourself From Statistical Lies: Part 1
Mean vs. Median and Why It Matters
--
COMING UPDATES: If you’d like to support my continuing to do this, you can send an Amazon giftcard to hollymathnerd at gmail or CashApp me at $HollyMathNerd. Thank you!
My statistical self-defense series has many other topics: go here for the list.
One of the easiest and most common ways of lying with statistics is to use the mean when the median would be the honest measure.
Suppose there are ten houses on your street. The cheapest is worth $200,000. The most expensive is worth $300,000. The mean, or average, of your street is about $250,000. Now imagine that a recently-canceled celebrity decides to spend his MeToo timeout on your street. He buys the corner lot and builds a mansion. That mansion is worth $2,000,000. Now the mean house value on your street has gone up to $409,090!
Saying that you live in “a $400,000 neighborhood” might help you on Tinder, but is it true? Do you want the property tax assessor to consider the value of Mr. Canceled’s house when she tabulates your bill?
The median is the middle value, and it is a much more honest value to use in situations like this.
A picture to help visualize the concept:
Next time you job-hunt, you’ll ask about median salaries, not average salaries, yes? The janitor and the CEO may have an average salary of $25,000,000.
