This thesis consists of three chapters on topics in Macroeconometrics.
Chapter 1 develops a hypothesis test to evaluate economic models and their forecasts robust to instabilities. The test is particularly powerful in the presence of multiple breaks and can be applied to in-sample and out-of-sample moment conditions. An application to predictability of the U.S. equity premium provides evidence in favor of "predictability pockets".
Chapter 2 investigates the evolution of the Federal Reserve information advantage and the information channel of U.S. monetary policy. It provides evidence that the information channel is historically relevant, but finds substantially weaker evidence of its presence in recent years, once instabilities are accounted for.
Chapter 3 develops a semi-parametric approach to conduct inference in non-Gaussian SVAR models robust to "weak" non-Gaussianity. The method exploits non-Gaussianity when it is present, while yielding correct coverage regardless of the distribution of the structural errors. An application revisits U.S. labor supply and demand elasticities and highlights the limitations of using non-Gaussianity for identification.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados