Template-Type: ReDIF-Paper 1.0
Author-Name: Florian Huber
Author-Name-First: Florian
Author-Name-Last: Huber
Author-Workplace-Name: University of Salzburg and International Institute for Applied Systems Analysis (IIASA)
Author-Name: Gary Koop
Author-Name-First: Gary
Author-Name-Last: Koop
Author-Workplace-Name: University of Strathclyde
Title: Fast and Order-invariant Inference in Bayesian VARs with Non-Parametric Shocks
Abstract: The shocks which hit macroeconomic models such as Vector Autoregressions
(VARs) have the potential to be non-Gaussian, exhibiting asymmetries
and fat tails. This consideration motivates the VAR developed in this
paper which uses a Dirichlet process mixture (DPM) to model the shocks.
However, we do not follow the obvious strategy of simply modelling the
VAR errors with a DPM since this would lead to computationally infeasible
Bayesian inference in larger VARs and potentially a sensitivity to the way the
variables are ordered in the VAR. Instead we develop a particular additive
error structure inspired by Bayesian nonparametric treatments of random
effects in panel data models. We show that this leads to a model which
allows for computationally fast and order-invariant inference in large VARs
with nonparametric shocks. Our empirical results with nonparametric VARs
of various dimensions shows that nonparametric treatment of the VAR errors
is particularly useful in periods such as the financial crisis and the pandemic.
Length:  pages
Creation-Date: 2023-05
Revision-Date: 
Publication-Status: 
File-URL: https://www.strath.ac.uk/media/1newwebsite/departmentsubject/economics/research/researchdiscussionpapers/2023/23-09.pdf
File-Format: Application/pdf
Number: 2309
Classification-JEL: C11, C32, C53
Keywords: Bayesian VARs, infinite mixtures, fast estimation, Markov chain Monte Carlo.
Handle: RePEc:str:wpaper:2309