统计研究

• 论文 • 上一篇    下一篇

Hawkes过程分支比估计 ——一种简单的非参数方法

吴奔 张波   

  • 出版日期:2015-03-15 发布日期:2015-04-28

Branching ratio estimation for the Hawkes process ——An Improved Nonparametric Methods

Wu Ben & Zhang Bo   

  • Online:2015-03-15 Published:2015-04-28

摘要: Hawkes自激发过程是近年来被广泛用于金融建模的一个良好模型。本文提出了一种Hawkes自激发过程的分支比的简单估计方法,该方法是对Hardiman和Bouchaud提出的均值-方差估计量的改进。在继承均值-方差估计量形式简便的优点的同时,克服其参数难以选择的缺陷,减小了估计的系统性偏差。模拟结果验证了改进的效果、同时我们将该估计方法用于我国股市内生性水平的分析之中。

关键词: Hawkes过程, 分支比, 内生性

Abstract: The self-exciting Hawkes process is a good model used widely in the field of financial modeling in recent years. We propose a simple approximation for the branching ratio of the self-exciting Hawkes process, which is an improvement based on the mean-variance estimator introduced by Hardiman and Bouchaud. The novel approach keeps the advantage of great simplicity as the mean-variance estimator, overcomes its difficulty of parameter selection, and furthermore reduces systematic biases. We perform simulations to verify the effect of our estimator and apply our method to study the level of endogeneity of the Chinese stock markets.

Key words: Central Bank Communication, Measurement, Wording, Spectral Analysis, Hawkes Process, Branching Ratio, Endogeneity