Forecasting risk measures using intraday and overnight information

• Published in: The North American journal of economics and finance 2022-04, Vol.60, p.101669, Article 101669
• Main Authors: Santos, Douglas G., Candido, Osvaldo, Tófoli, Paula V.
• Format: Article
• Language: English
• Subjects: Expected Shortfall; Overnight volatility; Realized volatility; Value-at-Risk; Volatility forecasting
• ISSN: 1062-9408; 1879-0860
• DOI: 10.1016/j.najef.2022.101669

Volatility forecasts are important for a number of practical financial decisions, such as those related to risk management. When working with high-frequency data from markets that operate during a reduced time, an approach to deal with the overnight return volatility is needed. In this context, we use heterogeneous autoregressions (HAR) to model the variation associated with the intraday activity, with distinct realized measures as regressors, and, to model the overnight returns, we use augmented GARCH type models. Then, we combine the HAR and GARCH models to generate forecasts for the total daily return volatility. In an empirical study, for returns on six international stock indices, we analyze the separate modeling approach in terms of its out-of-sample forecasting performance of daily volatility, Value-at-Risk and Expected Shortfall relative to standard models from the literature. In particular, the overall results are favorable for the separate modeling approach in comparison with some HAR models based on realized variance measures for the whole day and the standard GARCH model. •Separate modeling of the within-day and overnight volatilities.•Combinations of Heterogeneous Autoregressions and augmented GARCH type models.•Use of distinct realized variation measures as covariates.•Forecasting daily return volatility, Value-at-Risk and Expected Shortfall.•Favorable results for the separate modeling approach relative to competing models.