Evaluating strategic directional probability predictions of exchange rates

The current paper aims to examine strategic predictions (with forecast horizons greater than six months) via the empirical probability (EP) technique. This technique was proposed initially to examine short-term tactical predictions (with forecast horizons less than three months), as set out in Pollock et al. (2005). The proposed procedure is based on the hypothesis that changes in logarithms of daily exchange rates follow a normal distribution over short horizons (of 10 to 30 days), but longer term forecast evaluation requires consideration of cumulative parameters consistent with changing means and standard deviations arising from primary and secondary trends. It is shown that ex-post EPs can be obtained for any predictive horizon above 30 days (e.g., 180 days) by using a combination of shorter (e.g., 20-day) Student t distributions. The procedure is illustrated using daily Euro/USD series from 4 January 1999 to 29 January 2008 to evaluate a set of Euro/USD directional probability predictions.