The Objective Function of Simulation Estimators Near the Boundary of the Unstable Region of the Parameter Space
Year: 1998
Type: article
Abstract: The paper examines the role of stability constraints in estimation by dynamic simulation. In particular, it analyzes the behavior of the objective function on either side of the boundary of the stability region of the parameter space. The main finding is that stability constraints may be ignored because the simulation-based objective function contains a built-in penalty to enforce stability. A key caveat, however, is that the dynamic stability of the auxiliary model that defines the moment conditions must be checked and enforced. An attempt to fit via simulation to moments defined by a dynamically unstable auxiliary model can be expected to lead to an ill-behaved objective function.
Author: George Tauchen
Institution: Duke University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2156949537