Policy Inference Using Var Models

There has been relatively little systematic investigation of the sensitivity of policy inferences derived from VAR models to changes in the lag structure. We investigate this issue using a simple macro model consisting of output, prices, money and interest rates. Using six different lag length selection criteria that vary the bias‐efficiency tradeoff, we compare the policy inferences derived from the different estimations of our VAR model. The evidence shows that policy recommendations are quite sensitive to changes in the lag structure.