On Cointegration and Exchange Rate Dynamics





    Search for more papers by this author
    • Diebold is from the University of Pennsylvania, Gardeazabal is from the Universidad del Pais Vasco, and Yilmaz is from the University of Maryland. Helpful comments were received from the editor, René Stulz, and a referee, and from seminar participants at the North American Winter Meetings of the Econometric Society, the London School of Economics, the XVI Simposio de Análisis Economico (Barcelona), the University of Maryland, and the Penn Macro Lunch Group. We also thank Richard Baillie, Tim Bollerslev, Ken Kasa, Karen Lewis, Masao Ogaki, and Marta Regulez for useful comments. All remaining shortcomings are ours alone. The data were generously provided by Tim Bollerslev. We gratefully acknowledge financial support from the National Science Foundation, the Sloan Foundation, the University of Pennsylvania Research Foundation, and the Federal Reserve Bank of Philadelphia.


Baillie and Bollerslev (1989) have recently argued that nominal dollar spot exchange rates are cointegrated. Here we examine an immediate implication of their finding, namely, that cointegration implies an error-correction representation yielding forecasts superior to those from a martingale benchmark, in light of a large earlier literature highlighting the predictive superiority of the martingale. In an out-of-sample forecasting exercise, we find the martingale model to be superior. We then perform a battery of improved cointegration tests and find that the evidence for cointegration is much less strong than previously thought, a result consistent with the outcome of the forecasting exercise.