Granger-Causal-Priority and Choice of Variables in Vector Autoregressions
55 Pages Posted: 16 Oct 2013
There are 2 versions of this paper
Granger-Causal-Priority and Choice of Variables in Vector Autoregressions
Date Written: October 2013
Abstract
A researcher is interested in a set of variables that he wants to model with a vector autoregression 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-noncausality. 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.
Keywords: Bayesian model choice, Granger-causal-priority, Granger-noncausality, Structural vector autoregression, Vector autoregression
JEL Classification: C32, C52, E32
Suggested Citation: Suggested Citation
Here is the Coronavirus
related research on SSRN
Granger-Causal-Priority and Choice of Variables in Vector Autoregressions
This is a CEPR Discussion Paper. CEPR charges a fee of $8.00 for this paper.
If you wish to purchase the right to make copies of this paper for distribution to others, please select the quantity.
