Heteroscedasticity

Heteroscedasticity occurs when the variance of the errors in a regression model is not constant across all levels of the independent variables. In financial time series, this is the rule rather than the exception, as markets exhibit varying levels of volatility over time.

If a model assumes homoscedasticity when heteroscedasticity is present, the standard errors and confidence intervals will be biased, leading to poor risk assessments. Recognizing this property is essential for the valid application of statistical models in trading.

It requires the use of specialized estimators that account for the non-constant variance. Effectively modeling this is key to accurate derivative pricing and risk hedging.