Kurtosis

Kurtosis is a statistical measure that describes the shape of a probability distribution's tails relative to a normal distribution — specifically, how frequently extreme outcomes (both large gains and large losses) occur. A normal distribution has a kurtosis of 3 (or excess kurtosis of 0). High kurtosis (leptokurtic distribution, excess kurtosis greater than 0) indicates fat tails — extreme events occur more frequently than normal distribution models predict. Low kurtosis (platykurtic distribution) indicates thin tails. Equity returns — including those of Indian indices like Nifty 50 — typically exhibit high excess kurtosis (fat tails) and negative skewness, meaning crashes and extreme negative days are more common than a normal distribution would suggest. This has critical implications for risk models: Value at Risk (VaR) models that assume normally distributed returns systematically underestimate tail risk. For Indian institutional investors and options traders, accounting for excess kurtosis leads to better hedging strategies and more realistic assessment of worst-case scenario losses.