基于缓冲超越概率的风险度量及套期保值

尾部风险测度是风险管理中的关键点,本文利用缓冲超越概率模型,量化不同预期损失的风险概率分布,构建条件风险价值约束下的最小化“厚尾事件”概率的套期保值策略,从而将现有研究的视角拓展到考虑预期损失和风险概率的双重维度。本文通过实证数据统计和参数化拟合分布两个方法提供不同风险阈值及对应的缓冲超越概率的稳定解集合,研究结果发现,无论预期损失服从厚尾分布还是正态分布,缓冲超越概率模型均能够显著地降低市场风险和潜在的“厚尾事件”发生的概率,并提供比最小化方差稳定的套期保值比率。

Risk Measurement and Hedging Strategy Based on Buffer Probability of Exceedance Model

The risk measure of tail distribution is the key of risk management. This paper presents the probability distribution of different expected losses based on buffed Probability of Exceedance (bPOE), which offers a new insight into risk averse. Then it develops a hedging strategy based on minimum the probability of the heavy tail event and compares it with the strategy based on minimum variance. Furthermore, this paper calculates the set of the expected losses and their corresponding probabilities. The empirical results show that under the heavy tail distribution or normal distribution, the bPOE model reduces the expected loss and risk probability significantly, which offers the stable hedging effectiveness.