Fat Tail
Updated 2026-08-06
INTRODUCTION
English translation pending.
CORE DEFINITION
In a fat-tailed or heavy-tailed distribution, the probability of extreme values decays more slowly than in a normal distribution, so outliers occur far more often than standard models expect. Where outcomes follow a power law, a single extreme event can outweigh the sum of everything ordinary. Risk in such domains comes from the tail rather than the center, so the usual practice of treating small probabilities as negligible fails.
SCAFFOLDING EFFECT
Reduce cognitive load
- Identify the domain: check whether outcomes follow a power law or a bounded distribution. - Stress the tail: test the plan against extreme scenarios rather than against the average case. - Buy the insurance: hold redundancy and hedges sized for outcomes that could be terminal.
Anchor fast decisions
When the tail is heavy, the contribution of extreme values to the total is not bounded, so the mean of past observations carries little information about the next event. Protection sized for typical variation leaves the system exposed to the rare event that dominates the outcome. Surviving the tail therefore requires resources that look wasteful during normal periods.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Fat-tailed_distributionverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS