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.

Forecast combination, Forecast evaluation, Neural network model, Nonlinear forecasting, Nonlinear modelling
Time-Series Models; Dynamic Quantile Regressions (jel C22), Forecasting and Other Model Applications (jel C53),
International Journal of Forecasting
Erasmus Research Institute of Management

Terasvirta, T, van Dijk, D.J.C, & Medeiros, M. (2005). Linear models, smooth transition autoregressions, and neural networks for forecasting macroeconomic time series: A re-examination. International Journal of Forecasting, 21(4), 755–774. doi:10.1016/j.ijforecast.2005.04.010