Analyzing of Identifiability in Dynamic Stochastic General Equilibrium Models with Restrictions

This article is concerned with identification problem of parameters of Dynamic Stochastic General Equilibrium Models with covariance restrictions. We derived a set of identifiability conditions, and suggested a procedure for a thorough analysis of identification at each point in the parameters space. The procedure can be applied, before DSGE models are estimated, to determine where identification fails, and where it likely to be weak. We also used a Monte Carlo simulation and studied the effect of restrictions on the estimate. The results show that the use of covariance restrictions for estimation, when identification is reduced, leads us to inaccurate estimates and unreliable inference even when the number of observations is large.