Forecasting exchange rates with a large Bayesian VAR

Carriero, Andrea; Kapetanios, George; Marcellino, Massimiliano

doi:10.1016/j.ijforecast.2009.01.007

Cited by 146 publications

(93 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other variations, like the sum of coefficients (Doan et al, 1984) or the dummy initial observation prior (Sims, 1993), provide several options to alleviate the curse of dimensionality in a VAR. Especially in large models, variants of the priors discussed have been particularly successful in forecasting applications (Bańbura et al, 2010;Carriero et al, 2009;Giannone et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Huber

Feldkircher

2017

Journal of Business & Economic Statistics

101

105

View full text Add to dashboard Cite

Vector autoregressive (VAR) models are frequently used for forecasting and impulse response analysis. For both applications, shrinkage priors can help improving inference. In this paper we derive the shrinkage prior of Griffin et al. (2010) for the VAR case and its relevant conditional posterior distributions. This framework imposes a set of normally distributed priors on the autoregressive coefficients and the covariances of the VAR along with Gamma priors on a set of local and global prior scaling parameters. This prior setup is then generalized by introducing another layer of shrinkage with scaling parameters that push certain regions of the parameter space to zero. A simulation exercise shows that the proposed framework yields more precise estimates of the model parameters and impulse response functions. In addition, a forecasting exercise applied to US data shows that the proposed prior outperforms other specifications in terms of point and density predictions.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Huber

Feldkircher

2017

Journal of Business & Economic Statistics

101

105

View full text Add to dashboard Cite

show abstract

“…They propose Bayesian methods and impose additional information in form of a Minnesota-type prior to shrink the overparameterized VAR towards a parsimonious random walk (see also Carriero, Kapetanios, and Marcellino, 2009;Giannone, Lenza, and Primiceri, 2012;D'Agostino, Gambetti, and Giannone, 2013;Koop, 2013;Carriero, Clark, and Marcellino, 2014).…”

Section: Introductionmentioning

confidence: 99%

Point and density forecasts for the euro area using Bayesian VARs

Berg

Henzel

2015

International Journal of Forecasting

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Recent articles suggest that a Bayesian vector autoregression (BVAR) with shrinkage is a good forecast device even when the number of variables is large. In this paper we evaluate different variants of the BVAR with respect to their forecast accuracy for euro area real GDP growth and HICP inflation. We consider BVAR averaging, Bayesian factor augmented VARs (BFAVARs), and large BVARs, which differ in the way information is condensed and shrinkage is implemented. We find that: (a) large BVARs produce accurate point forecasts but show a poor performance when the entire density is considered; (b) BVAR averaging shows the opposite pattern; (c) BFAVARs perform well under both evaluation criteria; (d) choosing the degree of shrinkage optimally does not improve forecast accuracy; (e) all variants except the large BVAR tend to be well calibrated for inflation but poorly calibrated for real GDP growth; (f) these findings are robust to several features of the forecast experiment. Terms of use: Documents inJEL-Code: C110, C520, C530, E370.

show abstract

“…He concludes that allowing for stochastic volatility generally improves the accuracy of density forecasts. Recently, Carriero et al (2012) proposed a Bayesian VAR with stochastic volatility, which exploits the fact that most macroeconomic variables obey the same pattern of realized volatility. They conclude that imposing a factor structure on the latent log-volatilities helps to improve the accuracy of the density forecasts at little additional costs in terms of computational demands.…”

Section: Related Literaturementioning

confidence: 99%

“…13 Carriero et al (2009) show that controlling for co-movements of currencies is important to improve macroeconomic forecasts.…”

Section: Prior Implementationmentioning

confidence: 99%

“…We modify the Bayesian GVAR model with stochastic volatility as outlined by Huber (2014) and introduce a variant of the stochastic search variable selection (SSVS) prior. Using a restricted stochastic volatility model in the spirit of Carriero et al (2012) and a conjugate version of the SSVS prior leads to significant computational gains that are essential when estimating large-scale models such as the GVAR.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Does joint modelling of the world economy pay off? Evaluating global forecasts from a Bayesian GVAR

Dovern

Feldkircher

Huber

2016

Journal of Economic Dynamics and Control

View full text Add to dashboard Cite

We analyze how modeling international dependencies improves forecasts for the global economy based on a Bayesian GVAR with SSVS prior and stochastic volatility. To analyze the source of performance gains, we decompose the predictive joint density into its marginals and a copula term capturing the dependence structure across countries. The GVAR outperforms forecasts based on country-specific models. This performance is solely driven by superior predictions for the dependence structure across countries, whereas the GVAR does not yield better predictive marginal densities. The relative performance gains of the GVAR model are particularly pronounced during volatile periods and for emerging economies.JEL classification: C53, E37, F47 Keywords: GVAR, global economy, forecast evaluation, log score, copula * Corresponding author: Florian Huber, Oesterreichische Nationalbank (OeNB), Phone: +43-1-404 20-5208. E-mail: florian.huber@oenb.at. We would like to thank Hans Manner and all participants of the AWI seminar as well as the OeNB seminar for helpful comments on earlier drafts of this paper. The opinions expressed in this paper are those of the authors and do not necessarily reflect the official viewpoint of the OeNB or of the Eurosystem.

show abstract

Forecasting exchange rates with a large Bayesian VAR

Cited by 146 publications

References 16 publications

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Point and density forecasts for the euro area using Bayesian VARs

Does joint modelling of the world economy pay off? Evaluating global forecasts from a Bayesian GVAR

Contact Info

Product

Resources

About