Abstract

Forecasting risk measures in order to minimize and prevent a worse risk is an important and challenging task in quantitative risk management. Methodology and assessment of forecast accuracy are still developed to give a better risk measure forecast. In this paper, we provide a simple procedure to forecast expected-based risk measures of Value-at-Risk (VaR) and Expected Shortfall (ES). These risk measures may be determined by not only quantile but also expectile. By extending the Historical Simulation (HS) method and adopting the Monte Carlo (MC) principle, we build alternative algorithms without disregarding the (estimated) probability and/or distribution function(s) of the loss distribution. Based on the illustration for return data from New South Wales (NSW) Australian and Iranian electricity markets, it is found that our proposed method gives the expected-based risk measure forecast with better accuracy, instead of using the conventional HS method. The accuracy is getting higher when we consider the model able to capture the features of heavy-tailedness and conditional heteroscedasticity in the data.

摘要

预测风险措施以最小化和防止更严重的风险是定量风险管理中的一项重要且具有挑战性的任务。预测准确性的方法和评估仍在开发中，以提供更好的风险度量预测。在本文中，我们提供了一个简单的程序来预测基于预期的风险价值（VaR）和预期缺口（ES）的风险度量。这些风险度量不仅可以通过分位数来确定，还可以通过期望值来确定。通过扩展历史模拟（HS）方法并采用蒙特卡罗（MC）原理，我们构建了替代算法，而无需忽略损失分布的（估计）概率和/或分布函数。根据澳大利亚新南威尔士州 (NSW) 和伊朗电力市场返回数据的说明，结果发现，我们提出的方法比传统的 HS 方法给出了更准确的基于预期的风险度量预测。当我们考虑模型能够捕获数据中的重尾性和条件异方差性特征时，准确性会变得更高。