Evaluating Value-at-Risk models with desk-level data

Jeremy Berkowitz (), Peter F. Christoffersen and Denis Pelletier ()
Additional contact information
Jeremy Berkowitz: University of Houston

No 10, Working Paper Series from North Carolina State University, Department of Economics

Abstract: We present new evidence on disaggregated profit and loss and VaR forecasts obtained from a large international commercial bank. Our dataset includes daily P/L generated by four separate business lines within the bank. All four business lines are involved in securities trading and each is observed daily for a period of at least two years. Given this rich dataset, we provide an integrated, unifying framework for assessing the accuracy of VaR forecasts. A thorough Monte Carlo comparison of the various methods is conducted to provide guidance as to which of these many tests have the best finite-sample size and power properties. The Caviar test of Engle and Manganelli (2004) performs best overall but duration-based tests also perform well in many cases.

Keywords: risk management; backtesting; volatility; disclosure (search for similar items in EconPapers)
JEL-codes: G21 G32 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-ban, nep-ecm, nep-for and nep-rmg
Date: 2005-10, Revised 2006-12
View list of references View citations in EconPapers

Downloads: (external link)
ftp://ftp.ncsu.edu/pub/ncsu/economics/RePEc/pdf/BCP_12Dec06.pdf (application/pdf)

Related works:
Working Paper: Evaluating Value-at-Risk Models with Desk-Level Data (2008)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:ncs:wpaper:010

Access Statistics for this paper

More papers in Working Paper Series from North Carolina State University, Department of Economics
Contact information at EDIRC.
Series data maintained by Theofanis Tsoulouhas ().