This paper studies the implications of certain kinds of uncertainty for monetary policy. It first describes the optimum policy rule in a simple model of the transmission mechanism as in Ball and Svensson. It then examines how this rule ought to be modified when there is uncertainty about the parameters, about the time lags, or about the nature of shocks. The paper also discusses the case of a small open economy such as Canada's, with particular attention being given to uncertainty about the weights in a monetary conditions index.