Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/25079 
Year of Publication: 
2005
Series/Report no.: 
SFB 649 Discussion Paper No. 2005-060
Publisher: 
Humboldt University of Berlin, Collaborative Research Center 649 - Economic Risk, Berlin
Abstract: 
Risk management technology applied to high dimensional portfolios needs simple and fast methods for calculation of Value-at-Risk (VaR). The multivariate normal framework provides a simple off-the-shelf methodology but lacks the heavy tailed distributional properties that are observed in data. A principle component based method (tied closely to the elliptical structure of the distribution) is therefore expected to be unsatisfactory. Here we propose and analyze a technology that is based on Independent Component Analysis (ICA). We study the proposed ICVaR methodology in an extensive simulation study and apply it to a high dimensional portfolio situation. Our analysis yields very accurate VaRs.
Subjects: 
independent component analysis
Value-at-Risk
JEL: 
C14
C15
C32
C53
G20
Document Type: 
Working Paper

Files in This Item:
File
Size
715.43 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.