On the role of simulation in the statistical evaluation of econometric models (Q1118318)

Macro model builders routinely utilise the techniques of dynamic and static simulation for model selection and evaluation, as well as for discovering the properties of their models. Some researchers have suggested that the output of these simulations might be used for the purpose of formally evaluating models. The present paper looks at what information is conveyed by such simulations. It is argued that, because of relationships existing between the simulation residuals and estimation residuals, no new information is forthcoming from a simulation. Current proposals using simulation output for the purpose of model evaluation are analysed and it is shown that the same information could be extracted by a thorough analysis of the estimation residuals.