Long memory and nonlinearities in realized volatility: A Markov switching approach

详细信息	查看全文 | 推荐本文 |

• 作者：Davide Raggi^a ; ^{davide.raggi@unibo.it} ; Silvano Bordignon^b ; ^{bordigno@stat.unipd.it}
• 关键词：Realized volatility ; Switching-regime ; Long memory ; MCMC ; Forecasting
• 刊名：Computational Statistics and Data Analysis
• 出版年：2012
• 期刊代码：19_01679473
• 类别：cp
• 出版时间：November, 2012
• 卷：56
• 期：11
• 页码：3730-3742
• 文件大小：392 K

摘要

Realized volatility is studied using nonlinear and highly persistent dynamics. In particular, a model is proposed that simultaneously captures long memory and nonlinearities in which level and persistence shift through a Markov switching dynamics. Inference is based on an efficient Markov chain Monte Carlo (MCMC) algorithm that is used to estimate parameters, latent process and predictive densities. The in-sample results show that both long memory and nonlinearities are significant and improve the description of the data. The out-sample results at several forecast horizons show that introducing these nonlinearities produces superior forecasts over those obtained using nested models.