(), Dick van Dijk
() and Marcelo Medeiros
Timo Teräsvirta: Dept. of Economic Statistics, Stockholm School of Economics, Postal: Stockholm School of Economics, P.O. Box 6501, SE-113 83 Stockholm, Sweden
Dick van Dijk: Econometric Institute, Erasmus University Rotterdam, Postal: Econometric Institute, Erasmus University Rotterdam, P.O. Box 1738, NL-3000 DR Rotterdam , Netherlands
Marcelo Medeiros: Department of Economics, Pontifical Catholic University of Rio de Janeiro, Postal: Department of Economics, Pontifical Catholic University of Rio de Janeiro, Rua Marquês de São Vicente, 225 - Gávea, 22453-900 Rio de Janeiro, RJ, Brazil
Abstract: In this paper we examine the forecast accuracy of linear autoregressive, smooth transition autoregressive (STAR), and neural network (NN) time series models for 47 monthly macroeconomic variables of the G7 economies. Unlike previous studies that typically consider multiple but fixed model specifications, we use a single but dynamic specification for each model class. The point forecast results indicate that the STAR model generally outperforms linear autoregressive models. It also improves upon several fixed STAR models, demonstrating that careful specification of nonlinear time series models is of crucial importance. The results for neural network models are mixed in the sense that at long forecast horizons, an NN model obtained using Bayesian regularization produces more accurate forecasts than a corresponding model specified using the specific-to-general approach. Reasons for this outcome are discussed.
36 pages, First version: July 14, 2004. Revised: November 9, 2004. Earlier revisions: November 4, 2004.
Note: The paper will appear with Discussion by Professor Alfonso Novales and a reply by the authors.
Questions (including download problems) about the papers in this series should be directed to Helena Lundin ()
Report other problems with accessing this service to Sune Karlsson ().
This page generated on 2018-03-27 10:24:55.