统计研究 ›› 2018, Vol. 35 ›› Issue (5): 99-109.doi: 10.19343/j.cnki.11-1302/c.2018.05.010

• • 上一篇    下一篇

基于拟似然方法的股票收益与波动率关系及其应用研究

林金官等   

  • 出版日期:2018-05-25 发布日期:2018-05-25

The Relationship between Equity Yields and Volatility Based on Quasi-likelihood Approach as well as Its Application

Lin Jinguan et al.   

  • Online:2018-05-25 Published:2018-05-25

摘要: 股票市场中收益与波动率的关系研究在金融证券领域起着很重要的作用,而随机波动率模型能够很好地拟合这种关系。本文将拟似然方法和渐近拟似然方法运用在随机波动率模型的参数估计方面,渐近拟似然方法可以避免因为人为的结构错误指定而造成的偏差,比较稳健。本文采用拟似然和渐近拟似然方法对随机波动率模型的参数估计进行了模拟探索,并和两种已有估计方法进行了对比,结果表明拟似然和渐近拟似然方法在模型的参数估计方面有着很好的估计结果。实证研究中,选取2000-2015年标普500指数作为研究对象,结果显示所选数据具有金融时间序列的常见特征。本文为金融证券领域中股票收益与波动率关系及其应用研究提供了一定的启示。

关键词: 随机波动率模型, 拟似然, 核光滑方法;渐近拟似然

Abstract: The relationship between yields and volatility in stock market plays an important role in the field of financial securities, and the stochastic volatility model can fit it very well. This paper applies quasi-likelihood and asymptotic quasi-likelihood approaches to the parameter estimation of stochastic volatility model. The asymptotic quasi-likelihood approach is more robust as it can avoid the bias caused by the artificially misspecified structure. Simulation study is done in this paper to estimate the parameters in the stochastic volatility model using quasi-likelihood and asymptotic quasi-likelihood approaches, furthermore to compare with those from the other two methods available in the literature. The result shows that the proposed methods have performed well in parameter estimation. In the empirical analysis, by using the S&P 500 index from 2000 to 2015, and the result shows that the chosen data have the common characteristics in financial time series. This paper provides some implications for further study on the relationship between equity yields and volatility as well as its application.

Key words: Stochastic Volatility Model, Quasi-likelihood, Kernel Smoothing Method, Asymptotic Quasi-likelihood