Evaluating non-linear models on point and interval forecasts: an application with exchange rates

Gianna Boero () and Emanuela Marrocu

BNL Quarterly Review, 2005, vol. 58, issue 232, 91-120

Abstract: The aim of this paper is to compare the forecasting performance of SETAR and GARCHmodels against a linear benchmark using historical data for two bilateral dollarexchange rates, namely the Japanese Yen and the British Pound. The analysis is carried out with series sampled at weekly and daily frequencies. The relative performance of the models is evaluated on point forecasts and interval forecasts.Point forecasts evaluation tends to favour on average the linear models, though the analysis produces some evidence of forecasting gains from nonlinear models in sub-samples characterised by stronger non-linearity. Evaluation of interval forecastsclearly favours the GARCH models and shows that they are more accurate than the AR and SETAR models, especially at forecasting events in the tail regions of the distribution.

Keywords: Exchange; Rates (search for similar items in EconPapers)
JEL-codes: F31 F37 (search for similar items in EconPapers)
Date: 2005
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://ojs.uniroma1.it/index.php/PSLQuarterlyReview/article/view/9837/9722 (application/pdf)

Related works:
Journal Article: Evaluating non-linear models on point and interval forecasts: an application with exchange rates (2005)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:psl:bnlaqr:2005:14

Ordering information: This journal article can be ordered from
http://www.economiacivile.it

Access Statistics for this article

BNL Quarterly Review is currently edited by Alessandro Roncaglia

More articles in BNL Quarterly Review from Banca Nazionale del Lavoro
Bibliographic data for series maintained by Carlo D'Ippoliti ().