The out-of-sample success of term structure models as exchange rate predictors: a step beyond

A large literature suggests that standard exchange rate models cannot outperform a random walk forecast and that the forward rate is not an optimal predictor of the spot rate. However, there is evidence that the term structure of forward premia contains valuable information for forecasting future spot exchange rates and that exchange rate dynamics display nonlinearities. This paper proposes a term-structure forecasting model of exchange rates based on a regime-switching vector equilibrium correction model which is novel in this context. Our model significantly outperforms both a random walk and, to a lesser extent, a linear term-structure vector equilibrium correction model for four major dollar rates across a range of horizons. (C) 2002 Elsevier Science B.V. All rights reserved.