基于CARE模型的金融市场VaR和ES度量

The Estimation of Value at Risk and Expected Shortfall in Financial Market Based on CARE Models

次贷危机余波未了,欧债危机又风生水起。在此背景下,深入研究金融市场风险的度量方法及其预测防范机制,对推进金融市场改革、维护国家金融安全具有重要的参考价值。本文以期望分位数(Expectile)模型为基础,结合CAViaR模型,构建出条件自回归期望分位数模型(CARE),并以此来计算金融收益序列的VaR和ES,用以度量金融市场风险。通过对上证指数和深圳成指的实证分析发现:CARE模型在对金融收益序列的VaR估计和预测方面,明显优于风险管理实务界主流的RiskMetrics模型,也优于CAViaR模型,而且在ES度量方面也有着非常明显的优势。

Influence of the subprime crisis has not eliminated,while the European debt crisis is blustering. In this context, an in-depth study of the financial market risk has played an important role on the development of China＇ s economy. This paper proposes the Conditional Autoregressive Expectile models, which is based on Asymmetric Least Squares and CAViaR models, to estimate VaR and ES. Thus, the financial market risk can be described by CARE models. The empirical results show that CARE models are better than RiskMetrics and CAViaR models in estimating VaR. Furthermore, the CARE models have distinct advantages in estimating ES.