00000nam 2200000za 4500 9.807315 CaOODSP 20240219183354 cr ||||||||||| 150723s2014 oncd ob f000 0 eng d CaOODSP eng eng fre n-cn--- D68-2/62-2014E-PDF Maybury, David W. Foreign exchange value-at-risk with multiple currency exposure [electronic resource] : a multivariate and copula generalized autoregressive conditional heteroskedasticity approach / David W. Maybury. [Ottawa] : Defence Research and Development Canada, 2014. viii, 42, [2] p. : fig., graphs, tables. Scientific report ; 2014-R62 November 2014. Includes bibliographical references. Large DND projects and acquisitions are exposed to more than one foreign currency at the same time which complicates management’s foreign exchange risk assessments. The Centre for Operational Research and Analysis’ (CORA) in-house Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models are extended to a full multivariate setting. The extensions involve two models types: multivariate GARCH and copula-GARCH. It was found that both models give qualitatively similar value-at-risk (VaR) estimates, and that both models provide a much improved risk assessment relative to the current practice – correcting VaR estimates on the order of 25% in cases in which multiple currency exposures are of similar size. Using the USDCAD, the EURCAD, and the GBPCAD, estimation techniques for each model are demonstrated. Finally, the strength of the improved models are shown through a 100-day VaR calculation. gccst Purchasing gccst Foreign payments gccst Risk management Defence R&D Canada. Scientific report (Defence R&D Canada) 2014-R62 (CaOODSP)9.802305 PDF 861 KB https://publications.gc.ca/collections/collection_2015/rddc-drdc/D68-2-62-2014-eng.pdf DRDC-RDDC-2014-R62