Bayesian analysis of vector-autoregressive models with noninformative priors

✍ Scribed by Dongchu Sun; Shawn Ni

• Publisher: Elsevier Science
• Year: 2004
• Tongue: English
• Weight: 288 KB
• Volume: 121
• Category: Article
• ISSN: 0378-3758
• DOI: 10.1016/s0378-3758(03)00116-2

✦ Synopsis

In this paper, we investigate the properties of Bayes estimators of vector autoregression (VAR) coe cients and the covariance matrix under two commonly employed loss functions. We point out that the posterior mean of the variances of the VAR errors under the Je reys prior is likely to have an over-estimation bias. Our Bayesian computation results indicate that estimates using the constant prior on the VAR regression coe cients and the reference prior of Yang and Berger (Ann. Statist. 22 (1994) 1195) on the covariance matrix dominate the constant-Je reys prior estimates commonly used in applications of VAR models in macroeconomics. We also estimate a VAR model of consumption growth using both constant-reference and constant-Je reys priors.