Spreadwhen averages lie
Same average, different risk. Variance and standard deviation measure the honesty an average leaves out.
Before this
Next in Statistics
Conditional probabilityStatistics, stop 6 of 102 minThis opens up
Nothing yet. No lesson builds on this one so far.
Transcript
It follows the voice. Click a sentence to jump there.
Two summer jobs, both paying an average of one hundred dollars a day. Job A pays exactly one hundred, every single day. Job B flips a coin each morning: a bad day pays nothing, a good day pays two hundred. The averages match to the penny. The lives don't — one is a steady paycheck, the other is a gamble.
The difference has a name: spread — how far outcomes sit from their average. Pile each job's days into a distribution. Job A's days stack into a single spike, dead on the mean. Job B's days split into two towers, each one a hundred dollars from the center. Same center, completely different shape.
Measure it by asking each day: how far from the mean did you land? Job A's answer is always zero. Job B's answer is always one hundred dollars. Square those distances and average them — that's the variance. Take the square root to get back to dollars: that is the standard deviation, the typical distance from the mean. Job A: zero. Job B: one hundred. The gamble now has a number.
This one number decides real things. A medicine dose with the correct average but a wide spread overdoses one patient and shortchanges the next. A bridge built for the average load must still hold its heaviest day. And two investments with the same average return are different bets when one of them swings ten times harder. Same average everywhere — the risk hides in the spread.
An average is one number pretending to be a whole distribution. It marks the center, and it stays silent about how far the days stray from it. Spread is the honesty the average leaves out. Both jobs pay one hundred dollars a day — and only their spread can tell the steady paycheck from the coin flip.