我国中小板、创业板数据实证研究

发布时间：2018-05-09 04:06

本文选题：中小板 + 创业板　；参考：《中南大学》2013年硕士论文

【摘要】：对金融市场风险的测量一直是金融理论界和实业界都非常关心的课题,如果能够对市场风险进行预测,便能够从中获得可观的收益,于是,对市场价格的预测便显得非常重要。本文在总结近几年来国内外对高低频时间序列研究的基础上,以我国中小板、创业板1分钟、5分钟、15分钟、30分钟、60分钟和每日的股票指数数据为研究基础,从对数收益率及其波动率的角度出发,在运用金融时序分析的基础上进一步改进模型,通过建立更具有实际应用意义的HAR-WRV-GARCH-VaR模型,重点对中国金融市场的中小板、创业板的高频时序数据进行实证分析,并得出相关结论。本文主要从以下几个方面进行研究：首先,对我国中小板和创业板两市的高频时间序列进行初步统计分析,发现我国中小板、创业板的高频时间序列具有许多与低频时间序列不同的特征,因此原有可以在低频时间序列研究运用的模型和研究方法并不能完全运用于对高频时间序列的研究。其次,针对我国中小板、创业板市场指数进行了ARIMA(1,1,1,)模型的建立及求解,并对模型该模型的效果进行分析,发现该模型的效果不佳。继而,通过引入了长记忆性这一概念,逐步对上述模型进行深层次改进,提出了HAR-WRV-GARCH模型。紧接着以创业板为例,对我国创业板市场股票波动率进行了实证研究,并建立了HAR-WRV-GARCH(1,1)模型,然后对该模型进行了求解。最后在总结前面模型的基础上,建立HAR-WRV-GARCH-VaR模型,并以创业板市场为例,得出了创业板每日VaR值的计算公式,使得本文提出的模型具有了实际应用的价值及意义。
[Abstract]:The measurement of financial market risk has always been a topic of great concern to the financial theorists and businessmen. If we can predict the market risk, we can get considerable income from it. Therefore, it is very important to predict the market price. On the basis of summing up the research on high and low frequency time series at home and abroad in recent years, this paper studies the stock index data of China's small and medium sized boards, gem's 1 minute / 5 min / 15 min / 30 min / 60 min and daily stock index. From the point of view of logarithmic rate of return and its volatility, the model is further improved on the basis of financial time series analysis. Through the establishment of HAR-WRV-GARCH-VaR model with more practical significance, the emphasis is placed on the small and medium-sized boards of Chinese financial market. The high frequency time series data of gem are analyzed empirically, and the relevant conclusions are drawn. This article mainly carries on the research from the following several aspects: first, carries on the preliminary statistical analysis to our country small and medium-sized board and the growth enterprise board two cities high frequency time series, discovered our country small and medium-sized board, The high frequency time series of gem have many different characteristics from those of low frequency time series, so the models and research methods that can be used in the study of low frequency time series can not be fully applied to the study of high frequency time series. Secondly, aiming at the small and medium scale board of our country, the market index of gem is established and solved by Arima 1 / 1) model, and the effect of the model is analyzed, and it is found that the effect of this model is not good. Then, by introducing the concept of long memory, the HAR-WRV-GARCH model is proposed by improving the above model step by step. Then taking the gem as an example, this paper makes an empirical study on the volatility of the gem in China, and establishes the HAR-WRV-GARCH1) model, and then solves the model. Finally, on the basis of summarizing the previous models, the HAR-WRV-GARCH-VaR model is established, and taking the gem market as an example, the calculation formula of the daily VaR value of the gem is obtained, which makes the model presented in this paper have practical application value and significance.
【学位授予单位】：中南大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F832.51;F224

【参考文献】