Template-Type: ReDIF-Paper 1.0
Author-Name: Todd Clark
Author-Name-First: Todd
Author-Name-Last: Clark
Author-Workplace-Name: Federal Reserve Bank of Cleveland
Author-Name: Florian Huber
Author-Name-First: Florian
Author-Name-Last: Huber
Author-Workplace-Name: University of Salzburg
Author-Name: Gary Koop
Author-Name-First: Gary
Author-Name-Last: Koop
Author-Workplace-Name: University of Strathclyde
Author-Name: Massimiliano Marcellino
Author-Name-First: Massimiliano
Author-Name-Last: Marcellino
Author-Workplace-Name: Bocconi University, IGIER and CEPR
Author-Name: Michael Pfarrhofer
Author-Name-First: Michael
Author-Name-Last: Pfarrhofer
Author-Workplace-Name: University of Salzburg
Title: Investigating Growth at Risk Using a Multi-country Non-parametric Quantile Factor Model
Abstract: We develop a Bayesian non-parametric quantile panel regression model. Within
each quantile, the response function is a convex combination of a linear model and
a non-linear function, which we approximate using Bayesian Additive Regression
Trees (BART). Cross-sectional information at the pth quantile is captured through
a conditionally heteroscedastic latent factor. The non-parametric feature of our
model enhances 
exibility, while the panel feature, by exploiting cross-country
information, increases the number of observations in the tails. We develop Bayesian
Markov chain Monte Carlo (MCMC) methods for estimation and forecasting with
our quantile factor BART model (QF-BART), and apply them to study growth at
risk dynamics in a panel of 11 advanced economies
Length:  pages
Creation-Date: 2021-10
Revision-Date: 
Publication-Status: 
File-URL: https://www.strath.ac.uk/media/1newwebsite/departmentsubject/economics/research/researchdiscussionpapers/2023/23-07.pdf
File-Format: Application/pdf
Number: 2307
Classification-JEL: C11, C32, C53
Keywords: non-parametric regression, regression trees, forecasting
Handle: RePEc:str:wpaper:2307