The Hawkes model is suitable for describing self and mutually exciting random events. In addition, the exponential decay in the Hawkes process allows us to calculate the moment properties in the model. However, due to the complexity of the model and formula, few studies have been conducted on the performance of Hawkes volatility. In this study, we derived a variance formula that is directly applicable under the general settings of both unmarked and marked Hawkes models for tick-level price dynamics. In the marked model, the linear impact function and possible dependency between the marks and underlying processes are considered. The Hawkes volatility is applied to the mid-price process filtered at 0.1-second intervals to show reliable results; furthermore, intraday estimation is expected to have high utilization in real-time risk management. We also note the increasing predictive power of intraday Hawkes volatility over time and examine the relationship between futures and stock volatilities.
翻译:霍克斯模型适合于描述自我和相互刺激的随机事件。 此外,霍克斯工艺中的指数衰减让我们能够计算模型中的瞬间特性。然而,由于模型和公式的复杂性,对霍克斯波动性的表现进行了很少的研究。在本研究中,我们得出了一个在不记名和标记的霍克斯模型的一般设置下直接适用于刻度价格动态的差异公式。在标记模型中,考虑了线性撞击功能和标记与基本过程之间可能存在的依赖性。霍克斯的波动适用于中价进程,以0.1秒的间隔过滤法过滤,以显示可靠的结果;此外,在实时风险管理中,预计日内估计会得到高利用。我们还注意到日内霍克斯波动随着时间推移而不断增强的预测力,并研究未来与股票挥发性之间的关系。