Fat Tails (Kurtosis)
Fat tails describe return distributions in which extreme moves occur far more often than a normal distribution predicts; kurtosis is the statistic that measures this. It is closely related to Conditional Value at Risk (Expected Shortfall), Value at Risk (VaR), Volatility and Monte Carlo Simulation, each defined in the hedgewing.ai glossary.
If daily stock returns were normally distributed, a five-standard-deviation move would happen roughly once every 14,000 years. In practice such moves occur every few years in major indices and far more often in individual stocks. The distribution of real returns has 'fat tails': more mass in the extremes and a sharper peak in the middle than the bell curve allows. Kurtosis measures this; a normal distribution has a kurtosis of 3, and excess kurtosis above zero indicates fatter tails.
Fat tails are the reason risk models built on normal assumptions underestimate danger. A VaR computed from a normal distribution will be breached more often than its confidence level suggests, and losses when it is breached will be larger. Individual stocks are worse than indices in this respect, because earnings announcements, guidance changes, and regulatory news produce gap moves that no amount of recent calm foreshadows.
Practical responses include using historical or simulated distributions rather than normal ones for VaR, reporting conditional VaR to describe the tail, sizing positions on the assumption that something worse than the backtest will happen, and diversifying so that a single name's tail event is survivable. hedgewing.ai's VaR figures at 95% and 99% are meant to be read alongside the stock's volatility history, and investors should treat the 99% number as a floor rather than a ceiling on what can go wrong.
FAQ
What is Fat Tails (Kurtosis)?
Fat tails describe return distributions in which extreme moves occur far more often than a normal distribution predicts; kurtosis is the statistic that measures this.
Which terms are related to Fat Tails (Kurtosis)?
Fat Tails (Kurtosis) is closely related to Conditional Value at Risk (Expected Shortfall), Value at Risk (VaR), Volatility and Monte Carlo Simulation. Each has its own entry in the hedgewing.ai glossary.
Is this definition of Fat Tails (Kurtosis) investment advice?
No. This glossary entry explains what Fat Tails (Kurtosis) means. It is educational reference material, not personalised investment advice and not a recommendation to buy or sell any security.
Create a free Hedgewing account to try hedgewing.ai yourself.