An application of probability judgement accuracy measures to currency forecasting

A general framework for examining the quality of judgement in a currency forecasting context is described. This framework incorporates existing probability judgement accuracy measures and adapts them in a way that takes full advantage of the precise nature of exchange rate time series data. It also includes error measures, which are widely used in time series contexts, and adapts them to a probabilistic form in order to provide additional information in specific circumstances. The advantages of the proposed measures are outlined and an application to some actual currency data is provided. The framework is described initially to deal with directional forecasts and then extended to deal with point value, statistical and composite forecasts.