This paper presents empirical evidence on the monetary model of exchange rate determination that is in contrast with the bulk of existing empirical evidence. The Johansen multivariate technique of cointegration is applied to an unrestricted form of a version of the monetary model that allows distinction between traded and non-traded goods. Using three exchange rates and monthly data covering the period 1975–86, strong evidence is found in favour of the existence of cointegration between nominal exchange rate and a vector of explanatory variables. Furthermore, statistical testing of restrictions on the coefficients in the monetary model leads to the rejection of the restrictions except for some in the case of Germany. Two conclusions are reached: the monetary model can still be a valid representation of the long-run behaviour of exchange rates; and that the restrictions imposed on the model are in general not valid and may have been a factor contributing to the failure of the model in previous studies. How...