Bayesian analysis of recursive SVAR models with overidentifying restrictions
Bayesian analysis of recursive SVAR models with overidentifying restrictions

Summary/Abstract: The paper provides a Bayesian methodological framework for the estimation of structural vector autoregression (SVAR) models with recursive identification schemes that allows for the inclusion of overidentifying restrictions. The proposed framework enables the researcher (i) to elicit the prior on non-zero contemporaneous relations between economic variables and (ii) to derive an analytical expression for the posterior distribution and marginal data density. We illustrate our methodological framework by estimating a New-Keynesian SVAR model for Poland.

• Details
• Contents