Global Identification in Nonlinear Semiparametric Models

This paper derives primitive conditions for global identification in nonlinear simultaneous equations systems. Identification is semiparametric in the sense that it is based on a set of unconditional moment restrictions. Our contribution to the literature is twofold. First, we derive a set of unconditional moment restrictions on the observables that are the starting point for identification in nonlinear structural systems even when multiple equilibria are present. Second, we provide primitive conditions under which a parameter value that solves those restrictions is unique. We apply our results to a nonlinear transformed regression model with multiple equilibria and give sufficient conditions for identifiability of

its parameters.

For more information, contact Frank Schorfheide.