Does money still matter for U.S. output?

In this note, we use multivariate models estimated with Bayesian techniques and an out-ofsample approach to investigate whether money growth Granger-causes output growth in the United States. We find surprisingly strong evidence for a money-output link over the 1960-2005 period. However, further analysis indicates that this result is likely to be misleading; after the Great moderation, the Granger-causal role of money appears to have vanished completely.