Rights statement: This is the author’s version of a work that was accepted for publication in European Economic Review. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in European Economic Review, 141, 2022 DOI: 10.1016/j.euroecorev.2021.103952
Accepted author manuscript, 1.38 MB, PDF document
Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Estimation of large dimensional time varying VARs using copulas
AU - Tsionas, Mike G.
AU - Izzeldin, Marwan
AU - Trapani, Lorenzo
N1 - This is the author’s version of a work that was accepted for publication in European Economic Review. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in European Economic Review, 141, 2022 DOI: 10.1016/j.euroecorev.2021.103952
PY - 2022/1/31
Y1 - 2022/1/31
N2 - This paper provides a simple, yet reliable, alternative to the (Bayesian) estimation of large multivariate VARs with time variation in the conditional mean equations and/or in the covariance structure. The original multivariate, n-dimensional model is treated as a set of n univariate estimation problems, and cross-dependence is handled through the use of a copula. This makes it possible to run the estimation of each univariate equation in parallel. Thus, only univariate distribution functions are needed when estimating the individual equations, which are often available in closed form, and easy to handle with MCMC (or other techniques). Thereafter, the individual posteriors are combined with the copula, so obtaining a joint posterior which can be easily resampled. We illustrate our approach using various examples of large time-varying parameter VARs with 129 and even 215 macroeconomic variables.
AB - This paper provides a simple, yet reliable, alternative to the (Bayesian) estimation of large multivariate VARs with time variation in the conditional mean equations and/or in the covariance structure. The original multivariate, n-dimensional model is treated as a set of n univariate estimation problems, and cross-dependence is handled through the use of a copula. This makes it possible to run the estimation of each univariate equation in parallel. Thus, only univariate distribution functions are needed when estimating the individual equations, which are often available in closed form, and easy to handle with MCMC (or other techniques). Thereafter, the individual posteriors are combined with the copula, so obtaining a joint posterior which can be easily resampled. We illustrate our approach using various examples of large time-varying parameter VARs with 129 and even 215 macroeconomic variables.
KW - Vector AutoRegression
KW - Time-varying parameters
KW - Heteroskedasticity
KW - Copulas
U2 - 10.1016/j.euroecorev.2021.103952
DO - 10.1016/j.euroecorev.2021.103952
M3 - Journal article
VL - 141
JO - European Economic Review
JF - European Economic Review
SN - 0014-2921
M1 - 103952
ER -