Abstract

© 1996 by Christopher A. Sims and Tao A. Zha. This paper may be freely reproduced for educational and research purposes so long as each copy contains this copyright notice and the copies are not sold, even to cover costs. This allows individual copying for personal use and classroom or seminar bulk copying if the copies are distributed free to participants. Yale University and Federal Reserve Bank of Atlanta, respectively. We thank Eric Leeper for comments on an earlier draft. The views expressed here are not necessarily those of the Federal If multivariate dynamic models are to be used to guide decision-making, it is important that it be possible to provide probability assessments of their results, for example to give error bands around forecasts or policy projections. In Sims and Zha [1995] we showed how to compute Bayesian error bands for impulse responses estimated from reduced form vector autoregressions

Citations