Long-run monetary neutrality under stochastic and deterministic trends

This paper studies long-run monetary neutrality when long-horizon regressions (LHR) are used as a vehicle to test it. We assume that money and/or output can be generated according to widely used persistent models. We combine these specifications and study the divergence rate of the t-statistic as an indication of a spurious relationship between money and output, and show that the presence of spurious evidence of non-neutrality is highly likely. We then propose a correct inferential procedure for testing the null hypothesis of no relationship in a LHR (finite-sample and asymptotic evidence supports the procedure). The latter is then applied to an international data set on money and output in order to test for long-run monetary neutrality. We find that neutrality holds for all countries.