The aim of this paper is to analyse the out-of-sample performance of SETAR models relative to a linear AR and a GARCH model using daily data for the euro effective exchange rate (euro-EER). The evaluation is conducted on point, interval and density forecasts, unconditionally, over the whole forecast period, and conditional on specific regimes. The results show that overall the GARCH model is better able to capture the distributional features of the series and to predict higher-order moments than the SETAR models. However, from the results there is also a clear indication that the performance of the SETAR models improves significantly conditional on being on specific regimes.