A warning on the use of the Cochrane-Orcutt procedure based on a money demand equation for the United States

We show that estimates of the elasticity if demand for money in the United States depend crucially on which of the three minima of the residual sum of squares is selected by the Cochrane-Orcutt procedure applied to a model which contains a lagged endogenous variable. The model constitutes the first real example of multiple minima obtainable by the Cochrane-Orcutt procedure -- with or without a lagged endogenous variable -- and is used to caution against routine use of this procedure.