Forecasting realized volatility: HAR against Principal Components Combining, neural networks and GARCH

详细信息    查看全文

• 作者：Dimitrios I. Vortelinos ; ^{dvortelinos@lincoln.ac.uk}
• 关键词：HAR ; Principal Components Combining ; Neural networks ; GARCH ; Forecasting
• 刊名：Research in International Business and Finance
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：39
• 期：part_PB
• 页码：824-839
• 全文大小：659 K
• 卷排序：39

文摘

This paper examines whether nonlinear models, like Principal Components Combining, neural networks and GARCH are more accurate on realized volatility forecasting than the Heterogeneous Autoregressive (HAR) model. The answer is no. The realized volatility property of persistence is too important to leave out of a realized volatility forecasting model. However, the Principal Components Combining model is ranked very close to HAR. Analysis is implemented in seven US financial markets: spot equity, spot foreign exchange rates, exchange traded funds, equity index futures, US Treasury bonds futures, energy futures, and commodities options.