Back to Search
Start Over
Threshold cointegration in international exchange rates:A Bayesian approach
- Source :
- International Journal of Forecasting. 35:458-473
- Publication Year :
- 2019
- Publisher :
- Elsevier BV, 2019.
-
Abstract
- This paper considers Bayesian estimation of the threshold vector error correction (TVECM) model in moderate to large dimensions. Using the lagged cointegrating error as a threshold variable gives rise to additional difficulties that typically are solved by utilizing large sample approximations. By relying on Markov chain Monte Carlo methods, we are enabled to circumvent these issues and avoid computationally-prohibitive estimation strategies like the grid search. Due to the proliferation of parameters, we use novel global-local shrinkage priors in the spirit of Griffin and Brown (2010). We illustrate the merits of our approach in an application to five exchange rates vis-a-vis the US dollar by means of a forecasting comparison. Our findings indicate that adopting a non-linear modeling approach improves the predictive accuracy for most currencies relative to a set of simpler benchmark models and the random walk.
- Subjects :
- Bayes estimator
502025 Ökonometrie
502018 Macroeconomics
Computer science
502047 Volkswirtschaftstheorie
05 social sciences
Bayesian probability
502018 Makroökonomie
Markov chain Monte Carlo
Random walk
Variable (computer science)
symbols.namesake
0502 economics and business
Hyperparameter optimization
Prior probability
502025 Econometrics
502047 Economic theory
Econometrics
symbols
050207 economics
Business and International Management
Error detection and correction
050205 econometrics
Subjects
Details
- ISSN :
- 01692070
- Volume :
- 35
- Database :
- OpenAIRE
- Journal :
- International Journal of Forecasting
- Accession number :
- edsair.doi.dedup.....b956b10af848ff71d7d191905cac0608