On the interpretation of policy effects from estimates of simultaneous systems of equations

The purpose of this paper is threefold: first, we warn analysts against the use of structural coefficient estimates alone for deducing quantitative inferences concerning many policy experiments. Second, we offer a potential solution to the problem by proposing a mutatis mutandis approach to deducing the 'full effect' of a policy change on the endogenous variables of the model. Finally, we show that this approach yields consistent estimates of the reduced form parameters, the true solution to the difficulty. An illustration is provided.