基于重要抽样技术的外汇期权组合非线性VaR模型

发布时间：2018-07-03 15:39

本文选题：外汇期权组合 + Delta-Gamma-Theta模型　；参考：《系统管理学报》2010年01期

【摘要】：为了克服极小概率事件发生概率估计的困难,提出了把重要抽样技术发展到外汇期权组合非线性VaR模型中,通过改变市场变量回报分布的期望向量和协方差矩阵,在相应区域产生更多的样本,使得该情形下不再是稀有事件Monte Carlo模拟,从而减少Monte Carlo模拟计算工作量,更精确地估计出组合的损失概率,而组合的损失概率是计算组合损失分布的分位点(VaR值)的必备条件。模拟结果表明,该算法比常用Monte Carlo模拟法的计算效率更有效,且能很大程度上减少所要估计的损失概率的方差。
[Abstract]:In order to overcome the difficulty of estimating the probability of occurrence of minimal probability events, an important sampling technique is developed into the nonlinear VaR model of foreign exchange options portfolio. By changing the expected vector and covariance matrix of the return distribution of market variables, we propose a new method for estimating the probability of occurrence probability. More samples are generated in the corresponding region, so that the Monte Carlo simulation is no longer a rare event in this case, thus reducing the workload of Monte Carlo simulation and estimating the loss probability of the combination more accurately. The loss probability of combination is the necessary condition to calculate the value of VaR. The simulation results show that the proposed algorithm is more efficient than the conventional Monte Carlo simulation method and can greatly reduce the variance of the loss probability to be estimated.
【作者单位】：浙江财经学院金融学院;
【基金】：国家自然科学基金资助项目(70771099) 中国博士后科学基金资助项目(20070421167)
【分类号】：F830;F224

【参考文献】