Threshold cointegration and adaptive shrinkage

Huber, Florian ORCID: and Zörner, Thomas (2017) Threshold cointegration and adaptive shrinkage. Department of Economics Working Paper Series, 250. WU Vienna University of Economics and Business, Vienna.


Download (329kB)


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 are typically solved by relying on large sample approximations. Relying on Markov chain Monte Carlo methods we circumvent these issues by avoiding 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-á-vis the US dollar and assess whether a given currency is over or undervalued. Moreover, we perform a forecasting comparison to investigate whether it pays off to adopt a non-linear modeling approach relative to a set of simpler benchmark models.

Item Type: Paper
Additional Information: Mr. Zörner gratefully acknowledges financial support from the Austrian National Bank, Jubilaeumsfond grant no. 16748.
Keywords: non-linear modeling, shrinkage priors, multivariate cointegration, exchange rate modeling
Classification Codes: JEL C11, C32, C53, F31, F47
Divisions: Departments > Volkswirtschaft
Depositing User: Claudia Tering-Raunig
Date Deposited: 07 Jun 2017 09:53
Last Modified: 02 Sep 2020 15:19


View Item View Item


Downloads per month over past year

View more statistics