沪深300指数期货投资的市场风险研究

发布时间：2018-04-09 07:20

本文选题：沪深300指数期货　切入点：市场风险　出处：《东北财经大学》2012年硕士论文

【摘要】：我国于2010年4月16日正式推出沪深300指数期货,弥补了我国金融期货的缺失。自上市至今,其成交量、成交金额以及持仓量都逐年稳步攀升,已逐渐发展成为我国金融市场最重要的金融衍生品之一。然而,投资金融衍生产品往往都会因衍生品自身存在的一定缺陷而具有较高的风险。因此,有效合理的度量其投资的市场风险就具有重要意义。本文主要研究沪深300指数期货投资的市场风险,大致分为四个部分。文章的第一部分主要介绍本文的选题背景和意义,阐述度量市场风险的国内外研究现状,同时还简要说明本文框架和创新点。第二部分简单概述沪深300指数期货和在险价值(VaR)的相关知识。第三部分依据投资者进行投资的目的不同,将投资者分为投机者、套期保值者和套利者。相比投机者和套期保值者,套利者的风险相对较小,而且情况较为复杂。因此,本文使用经典的VaR方法主要针对投机者和套期保值者面临的价格波动风险和基差风险进行市场风险度量的实证研究。第四部分总结全文,得出本文的研究结论与不足,并展望未来研究。在本文实证研究价格波动风险和基差风险的部分：对于投机者,本文利用沪深300期指当月连续合约日收益率序列研究其面临的价格波动风险。通过分析可知：该序列分布表现出非正态性,呈现出尖峰、左偏等特征;‘序列为平稳序列：序列自相关性统计不显著；并且该序列没有统计显著的ARCH效应。鉴于此,本文采用蒙特卡洛(MC)模拟和历史模拟(HS)法计算价格波动风险日VaR。实证结果表明：与历史模拟相比,蒙特卡洛模拟能合理有效地计算沪深300期指合约价格波动风险日VaR。对于进行套期保值的投资者,本文利用所选样本期内基差的变化序列研究其主要面临的基差风险。通过分析可知：该序列自相关性统计显著;与正态分布相比,序列分布呈现出尖峰、右偏等特点；并且该序列存在统计显著的ARCH效应。鉴于此,本文采用基于GED分布和t分布假设下的ARMA(2,1)-GARCH(1,1)模型计算基差风险日VaR。实证结果表明：与t分布假设相比,通过GED分布假设求得基差风险日VaR的效果更好。并且GED参数u=1.419928,说明GED分布能很好的描述分布的“厚尾”性质。通过利用GARCH模型对条件方差进行拟合,最终求得套期保值风险日VaR,并且该模型通过了有效性后验检验,这表明通过此种方法计算基差风险日VaR是有效可行的。
[Abstract]:China officially launched Shanghai and Shenzhen 300 Index Futures on April 16, 2010, which makes up for the lack of financial futures in China.Since listing, its turnover, transaction amount and positions have risen steadily year by year, and it has gradually developed into one of the most important financial derivatives in our financial market.However, the investment financial derivatives often have higher risk because of their own defects.Therefore, it is of great significance to measure the market risk of its investment effectively and reasonably.This paper mainly studies the market risk of Shanghai and Shenzhen 300 index futures investment, which is divided into four parts.The first part of this paper mainly introduces the background and significance of this paper, describes the domestic and foreign research status of measuring market risk, and also briefly explains the framework and innovation of this paper.The second part is a brief overview of Shanghai and Shenzhen 300 index futures and risk value VaR) related knowledge.In the third part, investors are divided into speculators, hedgers and arbitrages.Compared with speculators and hedgers, arbitrage risk is relatively small, and the situation is more complex.Therefore, this paper mainly uses the classical VaR method to study the market risk measurement based on the price volatility risk and the base risk faced by speculators and hedgers.The fourth part summarizes the full text, draws the conclusion and deficiency of this paper, and looks forward to the future research.In this paper, the empirical study of the risk of price volatility and base risk: for speculators, this paper studies the risk of price volatility by using the daily yield series of the continuous contract of the Shanghai and Shenzhen 300 futures index in the same month.Through analysis, we can see that the distribution of the sequence is non-normal, showing peak, and the left deviation isometric 'sequence is a stationary sequence, the autocorrelation statistics of the sequence is not significant, and there is no statistically significant ARCH effect in the sequence.In view of this, this paper uses Monte Carlo Monte Carlo simulation and historical simulation to calculate the daily VaR of price volatility risk.The empirical results show that compared with historical simulation, Monte Carlo simulation can reasonably and effectively calculate the daily VaR of Shanghai and Shenzhen 300 futures index contract price volatility risk.For hedging investors, the risk of base difference is studied by using the variation sequence of basis in the selected sample period.Through the analysis, we can know that the autocorrelation of the sequence is significant, compared with the normal distribution, the sequence has the characteristics of peak and right deviation, and there is statistically significant ARCH effect in the sequence.In view of this, this paper uses the ARMA-2GARCH1) model based on the assumptions of GED distribution and t-distribution to calculate the risk day of base risk.The empirical results show that compared with the t-distribution hypothesis, the GED distribution assumption is more effective to obtain the base risk day VaR.And the GED parameter U1. 419928 shows that the GED distribution can well describe the "thick tail" property of the distribution.By fitting conditional variance with GARCH model, the hedging risk day VaR is finally obtained, and the model has passed the validity posteriori test, which shows that it is effective and feasible to calculate the base risk day VaR by this method.
【学位授予单位】：东北财经大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：F224;F832.5

【参考文献】