Modeling exchange rates: smooth transitions, neural networks, and linear models

Author

Medeiros, Marcelo C. ; Veiga, Alvaro ; Pedreira, Carlos Eduardo

Author_Institution

Dept. of Econ., Pontificia Univ. Catolica do Rio de Janeiro, Brazil

Volume

12

Issue

4

fYear

2001

fDate

7/1/2001 12:00:00 AM

Firstpage

755

Lastpage

764

Abstract

The goal of this paper is to test and model nonlinearities in several monthly exchange rates time series. We apply two different nonlinear alternatives, namely: the artificial neural-network time series model estimated with Bayesian regularization; and a flexible smooth transition specification, called the neuro-coefficient smooth transition autoregression. The linearity test rejects the null hypothesis of linearity in 10 out of 14 series. We compare, using different measures, the forecasting performance of the nonlinear specifications with the linear autoregression and the random walk models

Keywords

Bayes methods; autoregressive processes; estimation theory; forecasting theory; foreign exchange trading; neural nets; time series; Bayesian regularization; estimation theory; exchange rates; forecasting; model nonlinearities; neural-network; smooth transition autoregression; time series; Artificial neural networks; Bayesian methods; Exchange rates; Feedforward neural networks; Linearity; Mathematical model; Neural networks; Predictive models; Testing; Vectors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.935089

Filename

935089