Remarks on the 'Bayesian' method of moments

Zellner has proposed a novel methodology for estimating structural parameters and predicting future observables based on two moments of a subjective distribution and the application of the maximum entropy principle-all in the absence of an explicit statistical model or likelihood function for the data. He calls his procedure the 'Bayesian method of moments' (BMOM). In a recent paper in this journal, Green and Strawderman applied the BMOM to a model for slash pine plantations. It is our view that there are inconsistencies between BMOM and Bayesian (conditional) probability, as we explain in this paper.