Research Seminar: Department of Econometrics and Business Statistics

10/26/2018 02:00 pm 10/26/2018 03:15 pm Australia/Melbourne Research Seminar: Department of Econometrics and Business Statistics

The Department of Econometrics and Business Statistics invites you to a research seminar 'Bayesian Inference for Structural Vector Autoregressions Identified by Markov-Switching Heteroskedasticity' presented by Dr Tomasz Wozniak from the University of Melbourne.

No RSVP is required.

Abstract summary

In this study, Bayesian inference is developed for structural vector autoregressive models in which the structural parameters are identified via Markov-switching heteroskedasticity. In such a model, restrictions that are just-identifying in the homoskedastic case, become over-identifying and can be tested. A set of parametric restrictions is derived under which the structural matrix is globally or partially identified and a Savage-Dickey density ratio is used to assess the validity of the identification conditions. For that purpose, a new probability distribution is defined that generalizes the beta, F, and compound gamma distributions. As an empirical example, monetary models are compared using heteroskedasticity as an additional device for identification. The empirical results support models with money in the interest rate reaction function.

Event Details

Date:
26 October 2018 at 2:00 pm – 3:15 pm
Venue:
Clayton Campus, Robert Menzies building, Room E3.65
Categories:
Econometrics and Business Statistics

Description

The Department of Econometrics and Business Statistics invites you to a research seminar 'Bayesian Inference for Structural Vector Autoregressions Identified by Markov-Switching Heteroskedasticity' presented by Dr Tomasz Wozniak from the University of Melbourne.

No RSVP is required.

Abstract summary

In this study, Bayesian inference is developed for structural vector autoregressive models in which the structural parameters are identified via Markov-switching heteroskedasticity. In such a model, restrictions that are just-identifying in the homoskedastic case, become over-identifying and can be tested. A set of parametric restrictions is derived under which the structural matrix is globally or partially identified and a Savage-Dickey density ratio is used to assess the validity of the identification conditions. For that purpose, a new probability distribution is defined that generalizes the beta, F, and compound gamma distributions. As an empirical example, monetary models are compared using heteroskedasticity as an additional device for identification. The empirical results support models with money in the interest rate reaction function.