This paper compares in‐sample and out‐of‐sample performances of parametric and non‐parametric early warning systems (EWS) for currency crises in emerging economies. The parametric EWS achieves superior out‐of‐sample results compared with the non‐parametric EWS. The policymaker faces a trade‐off when using EWS: greater cautiousness allows the policymaker to correctly call more crisis episodes, but this comes at the cost of issuing more false alarms. The benefit of correctly calling more currency crises needs to be traded off against the cost of issuing more false alarms and of implementing corrective policies prematurely.