Forecasting the realized volatility: the role of jumps

ABSTRACT

This article investigates the role of jump components dependent on the ABD-LM jump test in forecasting volatility. Our out-of-sample forecasting results show that compared with the ABD-LM jump component, its decomposition forms based on signed returns can significantly improve the models’ forecasting performance and our findings have important implications for investors and policymakers.

KEYWORDS:

• Realized volatility
• HAR-RV model
• ABD-LM jump test
• MCS

JEL CLASSIFICATION:

• C22
• C52
• C53

Additional information

Funding

This work is supported by the National Natural Science Foundation of China [grant number 71371157] and the Young Scholar Fund of Science & Technology Department of Sichuan Province [grant number 2015JQO010].