Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/154033 
Year of Publication: 
2013
Series/Report no.: 
ECB Working Paper No. 1600
Publisher: 
European Central Bank (ECB), Frankfurt a. M.
Abstract: 
A researcher is interested in a set of variables that he wants to model with a vector auto-regression and he has a dataset with more variables. Which variables from the dataset to include in the VAR, in addition to the variables of interest? This question arises in many applications of VARs, in prediction and impulse response analysis. We develop a Bayesian methodology to answer this question. We rely on the idea of Granger-causal-priority, related to the well-known concept of Granger-non-causality. The methodology is simple to use, because we provide closed-form expressions for the relevant posterior probabilities. Applying the methodology to the case when the variables of interest are output, the price level, and the short-term interest rate, we find remarkably similar results for the United States and the euro area.
Subjects: 
Bayesian model choice
granger-causal-priority
granger-noncausality
structural vector autoregression
Vector autoregression
JEL: 
C32
C52
E32
Document Type: 
Working Paper

Files in This Item:
File
Size
922.48 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.