Bayesian Methods for Dynamic Multivariate Models

TLDR

Dynamic multivariate models must provide probability assessments for forecasts or policy projections, yet existing Bayesian VAR presentations with error bands suffer from unresolved conceptual and numerical inconsistencies. The authors introduce prior information into reduced‑form and structural VAR models in a way that avoids substantial additional computational burden. Their method enables the use of a single, large dynamic framework—such as a twenty‑variable model—for policy projection tasks. © 1998 Economics Department, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association.

Abstract

If dynamic multivariate models are to be used to guide decisionmaking, it is important that probability assessments of forecasts or policy projections be provided. When identified Bayesian vector autoregression (VAR) models are presented with error bands in the existing literature, both conceptual and numerical problems have not been dealt with in an internally consistent way. In this paper, the authors develop methods to introduce prior information in both reduced-form and structural VAR models without introducing substantial new computational burdens. Their approach makes it feasible to use a single, large dynamic framework (for example, twenty-variable models) for tasks of policy projections. Copyright 1998 by Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association.