摘要
本文应用极值分布理论对金融收益序列的尾部进行估计,计算收益序列的在险价值VaR和预期不足ES来度量市场风险。通过伪最大似然估计方法估计的GARCH模型对收益数据进行拟合,应用极值理论中的GPD对新息分布的尾部建模,得到了基于尾部估计产生收益序列的VaR和ES值。采用上证指数日对数收益数据为样本,得到了度量条件极值和无条件极值下VaR和ES的结果。实证研究表明:在置信水平很高(如99%)的条件下,采用极值方法度量风险值效果更好。而置信水平在95%下,其他方法和极值方法结合效果会很好。用ES度量风险能够使我们了解不利情况发生时风险的可能情况。
The paper is concerned with tail estimation for financial return series and, in particular, the estimation of market risk such as value at risk VaR or the expected shortfall. We fit GARCH-models to return data using pseudo maximum likelihood and use a GPD-approximation suggested by extreme value theory to model the tail of the distribution of the innovations. We find that a conditional approach that models the conditional distribution of asset returns against the current volatility background is better suited for VaR estimation than an unconditional approach that tries to estimate the marginal distribution of the process generating the returns. In the empirical research we choose Shanghai stock-market index and find that ES is more efficient than VaR.
出处
《数量经济技术经济研究》
CSSCI
北大核心
2007年第3期118-124,133,共8页
Journal of Quantitative & Technological Economics
基金
2006年国家社会科学基金项目(06JY010)
2004年教育部重大项目(05JJD790005)
"吉林大学‘985工程’项目"
吉林大学经济分析与预测创新基地资助
