Dados do Trabalho

Título

IDENTI CATION OF STRUCTURAL VECTOR AUTOREGRESSIONS BY STOCHASTIC VOLATILITY

Resumo

We propose to exploit stochastic volatility for statistical identi cation of Structural Vector Autoregressive models (SV-SVAR). We discuss full and partial identi cation of the model and develop e cient EM algorithms for Maximum Likelihood inference. Simulation evidence suggests that the SV-SVAR works well in identifying structural parameters also under misspeci cation of the variance process, particularly if compared to alternative heteroskedastic SVARs. We apply the model to study the interdependence between monetary
policy and stock markets. Since shocks identi ed by heteroskedasticity may not be economically meaningful, we exploit the framework to test conventional exclusion restrictions as well as Proxy SVAR restrictions which are overidentifying in the heteroskedastic model."

Palavras-chave

structural vector autoregressions; identification by heteroskedasticity; stochastic volatility; MCMC.