Focused Information Criterion for Locally Misspecified Vector Autoregressive Models

This paper investigates the focused information criterion and plug-in average for vector autoregressive models with local-to-zero misspecication. These methods have the advantage of focusing on a quantity of interest rather than aiming at overall model t. Any (suciently regular) function of the parameters can be used as a quantity of interest. We determine the asymptotic properties and elaborate on the role of the locally misspecied parameters. In particular, we show that the inability to consistently estimate locally misspecied parameters translates into suboptimal selection and averaging. We apply this framework to impulse response analysis. A Monte Carlo simulation study supports our claims.

• View at Publisher

Free Full Text ( Final Version , 2mb )