基于高频数据的我国沪深股市量价关系研究

发布时间：2018-05-07 21:00

本文选题：高频数据 + 量价关系　；参考：《天津财经大学》2013年硕士论文

【摘要】：股票市场的诞生源自于社会经济的不断发展。如今,股票市场作为资本市场的重要组成部分,可以从某一方面体现宏观经济的变化情况,因此被人们称作“宏观经济的晴雨表”。股票市场中,股票价格和成交量是两个不断变化的量,也是最为直观的两个指标。价格的下跌经常伴随有成交量的下降,同样价格的上涨也会出现成交量的放大。为了进一步探索二者之间的关系,论文将对此进行研究。量价关系的研究具有深刻的理论意义和应用价值。第一,高频数据量价关系的研究能够让我们更清楚的了解金融市场的微观结构。外部信息的到达会引起股市的变化,而这种变化则通过量价的变动表现出来。交易量的变动部分反映了信息对股市的冲击,因此作为信息的替代变量,能更好的解释价格波动的原因；第二,量价关系的研究具有很高的应用价值,无论对于广大投资者还是应用于期货投资方面都有很好的指导和参考意义。论文在总结之前学者关于量价关系研究的基础上从静态和动态两个方面对我国沪深股市的量价关系进行了分析研究。首先,静态关系的研究论文主要运用了比较传统的统计学分析方法。由于交易量序列、收益率序列都为金融时间序列,因此论文采用了基本描述性统计、单位根检验、Granger非因果关系检验等方法分别对高频和低频数据进行分析,并对高频和低频数据的共性和区别进行了总结。同时运用自回归移动平均ARMA(p,q)模型对交易量进行回归,从而进一步分解出预期交易量和非预期交易量。其次,动态关系的研究论文主要采用了分位数回归模型和向量自回归(VAR)模型进行分析。分位数回归模型从不同分位数点上描述了量价间的关系。VAR模型描述了原始交易量、预期交易量、非预期交易量与收益率及收益率的波动率序列之间的关系,并通过做脉冲响应分析受到冲击后对变量之间的反应状态。论文的创新有以下两点：第一、论文选取5分钟为间隔的高频金融时间序列数据为样本运用分位数回归模型对量价关系进行研究,相比较低频数据而言能够更好的揭示量价之间的内在关系；第二,论文对高频数据和低频数据的特征作了对比分析,并对量价关系的研究进行了总结,为后来的研究者在量价关系研究方面提供了便利。
[Abstract]:The birth of the stock market derives from the continuous development of the social economy. Now, as an important part of the capital market, the stock market can reflect the changes in the macro-economy from a certain aspect. Therefore, the stock market is called the "barometer of macro economy". In the stock market, the stock price and volume are two constant changes, as well as the volume of stock market. The two most intuitive indicators. The fall in prices is often accompanied by a decline in the volume of turnover, and the same price increase will also appear in the volume of enlargement. In order to further explore the relationship between the two, the paper will study this.
The research on the relationship between quantity and price has profound theoretical significance and applied value. First, the study of the high frequency data price relationship can make us understand the microstructure of the financial market more clearly. The arrival of the external information will cause the change of the stock market, and the change is shown by the change of the price. The change of the volume of the transaction reflects the letter. The impact of interest on the stock market, so as a substitute for information, can better explain the reasons for the price fluctuation. Second, the study of the relationship between price and price has a very high value of application. It has good guidance and reference meaning both for the broad investors and the futures investment.
On the basis of the study of the relationship between price and price, the paper analyses the relationship between volume and price of China's Shanghai and Shenzhen stock markets on the basis of two aspects of static and dynamic aspects. First, the research papers on static relations mainly use the traditional statistical analysis method. Therefore, the paper uses the basic descriptive statistics, the unit root test, the Granger non causality test and other methods to analyze the high frequency and low frequency data respectively, and summarizes the generality and difference of the high frequency and low frequency data. At the same time, the autoregressive moving average ARMA (P, q) model is used to return the volume of the transaction, thus further decomposing Secondly, the research papers of dynamic relationship are mainly analyzed by Quantile Regression Model and vector autoregressive (VAR) model. The quantile regression model describes the relationship.VAR model between the quantity and price from different points of quantile, which describes the original volume, expected volume, unexpected volume and revenue. The relationship between the volatility sequence of rate and yield and impulse response analysis is used to analyze the state of response between variables.
The innovation of this paper is as follows: firstly, the paper selects the high frequency financial time series with 5 minute interval as the sample using the quantile regression model to study the relation of quantity and price. Compared with the low frequency data, it can better reveal the intrinsic relationship between the quantity and price; and second, the characteristics of the high frequency data and low frequency data are made in the paper. A comparative analysis is made, and the research on the relationship between volume and price is summarized, which provides convenience for later researchers in the study of the relationship between volume and price.

【学位授予单位】：天津财经大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F832.51;F224

【参考文献】