No. 37 · Risk · Statistics and Probability
Fat-Tailed Distributions
In some areas, extreme events are far more common than the bell curve says.
In the Almanac
“Mandelbrot’s cotton prices”, 1963 · “Twenty-five sigma”, 2007
Both stories in full, three ways to use it and where it misleads.
Get the AlmanacListen · Watch
Questions
What is Fat-Tailed Distributions?
In fat-tailed distributions, extreme outcomes are far more common than a bell curve suggests, so a few events can dominate the average. Wealth, market returns, city sizes, and book sales work this way, and risk models that assumed normal distributions underestimated the 2008 financial crisis.
How do you use Fat-Tailed Distributions?
When dealing with fat-tailed domains, plan for worst cases that are worse and more likely than they seem, and be wary of averages. On the upside, small bets with uncapped potential, in careers, investments, or creative work, can pay off far beyond what typical outcomes suggest.
When does Fat-Tailed Distributions matter?
Fat-Tailed Distributions is one of the 32 mental models for risk, the situations where you ask: What could go wrong, and what will I do if it does? Within that, it belongs to “Thinking in odds”, alongside Expected Value, Foxes vs Hedgehogs and Law of Large Numbers.
What is an example of Fat-Tailed Distributions?
Two stories show it at work: Mandelbrot’s cotton prices (1963) and Twenty-five sigma (2007). Both are told in full in The Mental Models Daily Almanac, which has two stories for each of its 365 models.
Which mental models are related to Fat-Tailed Distributions?
Normal Distribution, Power Law and Black Swan Event. Fat-Tailed Distributions itself comes from statistics and probability.