Working papers, Department of Economics, WU (Wirtschaftsuniversität Wien)
Threshold cointegration and adaptive shrinkage
() and Thomas Zörner
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 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.
Keywords: non-linear modeling, shrinkage priors, multivariate cointegration, exchange rate modeling; (follow links to similar papers)
JEL-Codes: C11,; C32,; C53,; F31,; F47; (follow links to similar papers)
Before downloading any of the electronic versions below
you should read our statement on
for viewing Postscript files and the
Acrobat Reader for viewing and printing pdf files.
Report other problems with accessing this service to Sune Karlsson ()
or Helena Lundin ().
Design Joakim Ekebom