Volatility Forecasting: Evidence from a Fractional Integrated Asymmetric Power Arch Skewed-T Model

Abstract

Predicting the one-step-ahead volatility is of great importance in measuring and managing investment risk more accurately. Taking into consideration the main characteristics of the conditional volatility of asset returns, I estimate an asymmetric Autoregressive Conditional Heteroscedasticity (ARCH) model. The model is extended to also capture i) the skewness and excess kurtosis that the asset returns exhibit and ii) the fractional integration of the conditional variance. The model, which takes into consideration both the fractional integration of the conditional variance as well as the skewed and leptokurtic conditional distribution of innovations, produces the most accurate one-day-ahead volatility forecasts. The study recommends to portfolio managers and traders that extended ARCH models generate more accurate volatility forecasts of stock returns.

Keywords: ARCH models, Fractional Integration, Intra-Day Volatility, Long Memory, Skewed-t Distribution, Value-at-Risk, Volatility Forecasting

JEL Classification: C32, C52, C53, G15