Abstract
This paper presents a dynamic model averaging approach for forecasting nominal exchange rates. This framework encompasses most of the approaches commonly used in the forecasting literature and also allows us to study parameters and model uncertainty in exchange rate forecasting. We focus on nine major trading currency pairs: AUD/USD, CAD/USD, CHF/USD, EUR/USD, GBP/USD, NOK/USD, NZD/USD, SEK/USD, and JPY/USD, where we use data for approximately the last two decades. We empirically show statistically and economically significant exchange rate predictability in the medium and long run, and we also present some findings on predictability even in the short run. We offer several theoretical explanations for these results on predictability.