Empirical studies of monetary economics

This dissertation collects three essays on empirical monetary economics.;The first chapter outlines the major issues and illustrates some of the challenges in conducting monetary policy.;The second uses a time varying coefficient vector autoregression to assess the importance of the learning component in the US postwar economy. The random coefficients are assumed to follow a mean reverting process around an unconditional mean that can be interpreted as the estimates of the coefficients from the reduced form of a rational expectation equilibrium model. The deviations from the unconditional mean are attributed to the learning behaviour of the agents about the value of the coefficients which regulate the economy. I estimate a monetary model for the post WWII U.S. economy including inflation, output growth and the federal funds rate. I document the presence of learning dynamics and find that the importance of the learning mechanism is somewhat limited for inflation and output growth but it is substantial in explaining the dynamics of the federal funds rate.;The third chapter deals with forecast evaluation. In particular, it introduces tests of Likelihood Ratio types for one sided multivariate hypothesis to evaluate the null that a parsimonious model performs equally well as a small number of models which nest the benchmark. The size and the power performance of the tests are compared with the ones of two existing tests: a chi-squared test, as described in Clark and West (2007) applied to multivariate comparison in Hubrich and West (2008), and the maximum of correlated normal test outlined in Hubrich and West (2008). The test statistics do not have a standard limiting distribution. Critical values are then obtained through simulations either adopting the assumption of normality or through subsampling. Under the normality assumption the LRT and correlated normal test are undersized but the size distortion decreases with the in-sample/out-of-sample ratio. The Monte Carlo experiments reveal that the chi-squared test performs poorly in terms of power as it disregard the one-sided nature of the test, while the ranking between the likelihood-ratio type test and the correlated normal test depends on the simulation settings. The results from the subsampling are sensitive to the choice of the block size. The tests are applied to evaluate the forecast accuracy of competing models for forecasting the yearly US aggregate inflation rate.