基于高频金融数据的中国股市波动性研究

发布时间：2018-01-05 03:03

本文关键词：基于高频金融数据的中国股市波动性研究　出处：《湖南师范大学》2013年硕士论文　论文类型：学位论文

【摘要】：随着计算机技术的发展和全球经济一体化进程的加快,高频金融数据的获得也越来越容易,高频金融数据波动率的估计逐渐成为当今的研究热点问题之一。一般情况下,股市的高频数据波动会表现出一些较低频数据不同的特点,刻画股市高频数据波动性就是为了能够准确地描绘了股市波动的典型特征和趋势,为股市风险管理提供理论支撑。本文以“已实现”波动率模型为基础,运用极差理论的方法,构造赋权“已实现”极差波动,并研究了不同频率的上证综指和深证成指的波动特征。在分析赋权“已实现”极差波动的统计特征的基础上,论文从微观层面出发,研究赋权“已实现”极差波动与交易量之间的相互作用关系。结果表明： (1)赋权“已实现”极差波动具有较小的方差,满足波动估计量的无偏性和有效性,且经对数化处理后基本符合正态分布,具有良好的统计性质。 (2)深证成指1分钟高频数据的波动与交易量间不存在Granger关系,而上证综指5分钟高频数据的波动与交易量互为Granger原因,这说明量价关系并不稳定,尤其是在新兴资本市场,很多投资者是属于盲目性投资,存在从众心理。 (3)对上证综指5分钟高频数据构建VAR模型,证实了波动与交易量之间存在联动性,模型解释了日内波动的聚集性,而且交易量的变动引起价格波动,这在一定程度上解释了收益波动的原因。同时,波动率也会反馈到交易量,进而影响交易量的变动。
[Abstract]:With the development of computer technology and the acceleration of the process of global economic integration, the acquisition of high-frequency financial data is becoming easier and easier. The estimation of volatility of high-frequency financial data has gradually become one of the hot issues. In general, the volatility of high-frequency data in stock market will show some different characteristics than low-frequency data. In order to accurately describe the typical characteristics and trends of stock market volatility, it can provide theoretical support for stock market risk management. Based on the "realized" volatility model, this paper uses the method of range theory to construct the weighted "realized" range fluctuation. And studied the volatility characteristics of Shanghai Composite Index and Shenzhen Composite Index with different frequencies. On the basis of analyzing the statistical characteristics of "realized" range fluctuation, the paper starts from the micro level. The interaction between the "realized" range fluctuation and the trading volume is studied. The results show that: 1) the weighted "realized" range fluctuation has small variance, which satisfies the unbiased and validity of the fluctuation estimator, and basically accords with the normal distribution after logarithmic treatment, and has good statistical properties. (2) there is no Granger relationship between the fluctuation of high-frequency data and trading volume in Shenzhen Composite Index, while the fluctuation and trading volume of 5-minute high frequency data in Shanghai Composite Index are mutual Granger reasons. This shows that the relationship between volume and price is not stable, especially in emerging capital markets, many investors are blind investment, there is herd mentality. Thirdly, the VAR model is constructed for the 5-minute high frequency data of Shanghai Composite Index, which proves that there is a linkage between volatility and trading volume. The model explains the aggregation of intraday volatility, and the fluctuation of trading volume causes price volatility. At the same time, the volatility will also feed back to the trading volume, and then affect the change of trading volume.
【学位授予单位】：湖南师范大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F832.51;F224

【参考文献】