This article proposes a new model for calculating VaR in which the user can choose any probability distributions for daily changes in the market are subject to updating schemes similar to GARCH. Transformations of the probability distributions are assumed to be multivariate normal,The model is appealing in that the calculation of VaR is relatively straighforward and can make use of the RiskMetrics or a similar data base.

We test a version of the model using nine years of daily data on twelve different exchange rates.When the first half of the data is used to estimate the models parameters, we find that it provides good predictions for the second half of the data.