Monitoring multi-country macroeconomic risk: a quantile factor-augmented vector autoregressive (QFAVAR) approach

Korobilis, D. and Schröder, M. (2024) Monitoring multi-country macroeconomic risk: a quantile factor-augmented vector autoregressive (QFAVAR) approach. Journal of Econometrics, (Accepted for Publication)

Abstract

A multi-country quantile factor-augmented vector autoregression is proposed to model heterogeneities both across countries and across characteristics of the distributions of macroeconomic time series. The presence of quantile factors enables a parsimonious summary of these two heterogeneities by accounting for dependencies in the cross-sectional dimension as well as across different quantiles of macroeconomic data. Using monthly euro area data, the strong empirical performance of the new model in gauging the impact of global shocks on country-level macroeconomic risks is demonstrated. The short-term tail forecasts of QFAVAR outperform those of FAVARs with symmetric Gaussian errors as well as univariate and multivariate specifications featuring stochastic volatility. Modeling individual quantiles enables scenario analysis of macroeconomic risks, a unique feature absent in FAVARs with stochastic volatility or flexible error distributions.

• Item Type: Articles
• Keywords: quantile VAR, multivariate quantiles, MCMC, dynamic factor model.
• Status: Accepted for Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Korompilis Magkas, Professor Dimitris
• Authors: Korobilis, D., and Schröder, M.
• Subjects: H Social Sciences > HA Statistics; H Social Sciences > HB Economic Theory
• College/School: College of Social Sciences > Adam Smith Business School > Economics
• Journal Name: Journal of Econometrics
• Publisher: Elsevier
• ISSN: 0304-4076
• ISSN (Online): 1872-6895

Related URLs

• Pre-print