基于价格条件VaR的投指期货套利研究

发布时间：2018-09-10 10:49

【摘要】：文章第二部分及第四部分分别运用时间序列方法,选取高频数据拟合了沪深300股指期货的差价套利模型及香港恒生指数、沪深300股指期货的比价套利模型,并运用价格条件VaR方法对其套利风险进行测算,并检验其有效性,预测效果较好。本文的重点及创新点在于套利点确定方法的研究。在差价套利部分,分别在正态分布和t分布的假设前提下,研究差价序列和对数差价序列的最优套利点确定方法及步骤,在比价套利部分,分别在正态分布和t分布的假设前提下,研究差价序列的最优套利点确定方法和步骤。本文运用计算最大套利期望收益的方法得到最优套利点,运用Lingo软件求其数值解。得到了以下结论：沪深300股指期货不同到期日合约间差价及其差价对数序列部分平稳,且香港恒生指数的估计值与真实值的价差均属于平稳时间序列。对比价套利模型进行转换,得到△P=u(?)=PHS-βHS,因此,比价套利模型的套利点确定方法与差价套利的思想和方法一致。以此为依据,研究得到了：在σ相同条件下,t分布的最大期望收益比正态分布高,伴随t分布自由度增大,最优套利点向正态分布的情景逼近。考虑交易成本的最优套利点,比不考虑交易成本的最优套利点离均值点更远,最优期望收益也更低。并且应该将跨期套利的△P07-12和△P09-12作为主要关注对象,而跨市场跨品种套利应该把△P10和△P12作为主要关注对象。
[Abstract]:The second part and the fourth part respectively use the time series method to select the high-frequency data to fit the price arbitrage model of the Shanghai and Shenzhen 300 stock index futures and the Hang Seng index of Hong Kong and the arbitrage model of the Shanghai and Shenzhen 300 stock index futures. The arbitrage risk is measured by price conditional VaR method, and its effectiveness is tested. The emphasis and innovation of this paper lies in the study of arbitrage point determination method. Under the assumption of normal distribution and t distribution, this paper studies the method and steps of determining the optimal arbitrage point of the difference sequence and the logarithmic difference sequence in the arbitrage part. Under the assumption of normal distribution and t distribution, the method and steps of determining the optimal arbitrage point of the difference sequence are studied. In this paper, the optimal arbitrage point is obtained by using the method of calculating the expected maximum arbitrage income, and the numerical solution is obtained by using Lingo software. The conclusions are as follows: the price difference and the logarithmic sequence of the price difference between the different maturity days of the Shanghai and Shenzhen 300 stock index futures are partially stable, and the difference between the estimated value and the real value of the Hang Seng Index in Hong Kong belongs to the stationary time series. In this paper, we convert the arbitrage model to get PHS- 尾 HS,. Therefore, the arbitrage point determination method of the arbitrage model is consistent with the idea and method of arbitrage at the price difference. Based on this, it is obtained that the maximum expected income of the t distribution is higher than that of the normal distribution under the same 蟽 conditions, the degree of freedom of the t distribution increases, and the optimal arbitrage point approximates to the normal distribution. The optimal arbitrage point considering the transaction cost is farther from the mean point and the optimal expected income is lower than the optimal arbitrage point without considering the transaction cost. And we should take P07-12 and P09-12 of intertemporal arbitrage as the main object of concern, while cross-market cross-variety arbitrage should take P10 and P12 as the main objects of concern.
【学位授予单位】：北方工业大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F224;F832.51

【参考文献】