Alternative Maximum Likelihood Estimation of Structural Vector Autoregressive Models Partially Identified with Short-Run Restrictions


  • This work was supported by Inha University Research Grant. I thank Masao Ogaki for the guidance and S.D. Lee for comments. I also thank two anonymous referees and seminar participants at the 2004 Far Eastern Econometric Society Meeting for valuable comments. I am completely responsible for any remaining errors and deficiencies.


This paper presents an alternative maximum likelihood estimation method for partially identified vector autoregressive models. This method might be especially useful to handle very large systems of variables by reducing the dimension of the likelihood space. As an application, we consider an open economy model to investigate the effects of monetary policy on exchange rates and term structures. We find that exchange rates tend to overshoot and term structures have hump-shaped responses to monetary policy shocks.