A New Approach to Assessing Model Risk in High Dimensions
A New Approach to Assessing Model Risk in High Dimensions
复制标题
DOI：
10.2139/ssrn.2393054
复制
发表时间：
2015-04
期刊：
影响因子：
--
通讯作者：
C. Bernard;S. Vanduffel
中科院分区：
文献类型：
--
作者：
C. Bernard;S. Vanduffel
对于监管者和风险管理者来说，一个核心问题是如何对一个总投资组合进行风险评估，该组合被定义为d个独立依赖风险Xi的总和。当X1，X2，…，Xd的联合分布完全确定后，这个问题主要是一个数值问题。不幸的是，虽然风险Xi的边际分布通常是已知的，但它们的相互作用（依赖性）通常是未知的或只是部分已知的，这意味着对投资组合的任何风险评估都受到模型不确定性的影响。
A central problem for regulators and risk managers concerns the risk assessment of an aggregate portfolio defined as the sum of d individual dependent risks Xi. This problem is mainly a numerical issue once the joint distribution of X1,X2,…,Xd is fully specified. Unfortunately, while the marginal distributions of the risks Xi are often known, their interaction (dependence) is usually either unknown or only partially known, implying that any risk assessment of the portfolio is subject to model uncertainty.