中国证券市场波动率的实证研究

发布时间：2018-02-11 04:10

本文关键词： 收益率波动率 ARCH模型 GARCH模型　出处：《山东大学》2017年硕士论文　论文类型：学位论文

【摘要】：中国证券市场经过了二十几年的发展,取得了巨大的成果,对整个国民经济做出了巨大的贡献,但是,中国证券市场还处于发展的初级阶段,基础还比较薄弱,各种政策制度还不够完善,在发展中暴露了很多问题,表现出了波动严重的不稳定性和明显的杠杆效应。中国证券市场中存在的问题,越来越受到投资者和专家学者的重视,这些问题对于改善中国金融市场具有重要的意义,所以本文的研究对象是中国证券市场的波动现象。随着现代金融市场的不断发展,人们发现ARCH族模型能够对市场波动进行有效地刻画,所以本文的研究方法是利用ARCH(GARCH)模型对波动率进行建模,从而较为精确的对金融市场上的风险进行度量,对风险的计量提出有价值的建议。本文以上证综指、深证综指及创业板指数的日收益率为基准,利用ARCH族模型并通过EViews软件描述了我国股票价格收益率的统计特征,并对中国证券市场的波动进行了实证分析,在前人研究的基础上,加入了成交量作为解释变量进行了更为深入的研究。通过研究我们发现,中国证券市场收益率的基本统计特征中,峰度都远远大于在正态分布下的3,具有过度峰度,说明了中国证券市场结构不够完善,收益率波动较为突出,且收益率序列都是不服从正态分布的,且收益率序列存在ARCH效应、杠杆效应和不对称性波动。在引入了成交量这一变量后,通过Granger因果关系检验,表明了上海证券市场和深圳证券市场的收益率和成交量之间是存在因果关系。当模型中加入了成交量后,反应股票价格波动持续性α1+β1的值减小了且拟合优度提高了,说明加入了成交量之后,确实更进一步的解释股票价格波动的原因。但是在创业板市场,成交量和股票价格波动的GRANGER因果关系的检验中,成交量变化率对收益率的波动并不能很好的解释,因为P值不显著。对加入了成交量的GARCH模型进行实证研究中,虽然成交量变化率的系数大于0,但是却对均值方差的拟合并不是很好,在5%显著水平下并不显著,更进一步的表明了成交量对于收益率的波动并不能很好的解释。
[Abstract]:After more than 20 years of development, China's securities market has made great achievements and made great contributions to the entire national economy. However, China's securities market is still in the initial stage of development and its foundation is still relatively weak. All kinds of policies and systems are not perfect enough, and many problems have been exposed in the course of development, showing serious volatility instability and obvious leverage effect. The problems existing in China's securities market have been paid more and more attention by investors and experts and scholars. These problems are of great significance to the improvement of China's financial market, so the object of this paper is the volatility of China's securities market. It is found that the ARCH family model can effectively depict the volatility of the market, so the research method of this paper is to use the Arch GARCH model to model the volatility, so as to measure the risk in the financial market more accurately. Based on the daily rate of return of Shanghai Composite Index, Shenzhen Composite Index and growth Enterprise Market Index, this paper describes the statistical characteristics of stock price rate of return in China by using ARCH family model and EViews software. On the basis of the previous studies, we add the trading volume as the explanatory variable to further study the volatility of China's securities market. Through the study, we find that, In the basic statistical characteristics of the return rate of China's securities market, kurtosis is far greater than that under normal distribution, which has excessive kurtosis, which indicates that the structure of China's securities market is not perfect, and the fluctuation of yield is more prominent. And the return series are all dissatisfied with normal distribution, and there are ARCH effect, leverage effect and asymmetry fluctuation in the return series. After introducing the variable of trading volume, Granger causality test is adopted. The results show that there is a causal relationship between the return rate and trading volume in Shanghai Stock Market and Shenzhen Stock Market. When the trading volume is added to the model, the value of 伪 1 尾 1, which reflects the volatility of the stock price, decreases and the goodness of fit increases. After adding the trading volume, it is true that the reason for the stock price fluctuation is further explained. But in the gem market, the GRANGER causality test of the volume and the stock price fluctuation, The change rate of turnover does not explain the volatility of yield because P value is not significant. The empirical study of GARCH model with turnover is carried out. Although the coefficient of change rate of turnover is greater than 0, the fitting of mean variance is not very good, and it is not significant at the level of 5%, which further shows that the trading volume does not explain the volatility of yield very well.
【学位授予单位】：山东大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：F832.51;O212.1

【参考文献】