Model reduction in dynamical VAR systems

In this paper, we propose an alternative method that applies the model reduction techniques to the VAR framework when the number of variables is sufficiently large. The relevance of the model reduction in the VAR and SVAR systems comes from that the new trajectories preserve the qualitative properties of the initial trajectories. In economic analysis, this allows us to apprehend the underlying phenomena. Also, the resulting model is accurate, computationally less expensive, and based on the real meaning of the system.