Bos, Charles S. Mahieu, Ronald J. van Dijk, Herman K.
Year of Publication:
Tinbergen Institute Discussion Paper 01-017/4
We construct models which enable a decision-maker to analyze the implications oftypical timeseries patterns of daily exchange rates for currency risk management. Ourapproach is Bayesianwhere extensive use is made of Markov chain Monte Carlo methods. The effects ofseveral modelcharacteristics (unit roots, GARCH, stochastic volatility, heavy taileddisturbance densities) areinvestigated in relation to the hedging strategies. Consequently, we can make adistinctionbetween statistical relevance of model specifications, and the economicconsequences from a riskmanagement point of view. We compute payoffs and utilities from severalalternative hedgestrategies. The results indicate that modelling time varying features ofexchange rate returns maylead to improved hedge behaviour within currency overlay management.