The aim of this paper is to evaluate the forecasting performance of SETAR models with an application to the Industrial Production Index (IPI) of four major European countries over a period which includes the last Great Recession. Both point and interval forecasts are considered at different horizons against those obtained from two linear models. We follow the approach suggested by Teräsvirta et al. (2005) according to which a dynamic specification may improve the forecast performance of the nonlinear models with respect to the linear models. We re-specify the models every twelve months and we find that the advantages of this procedure are particularly evident in the forecast rounds immediately following the re-specification.

The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Our main goal in this paper is to evaluate the point forecasting accuracy of several time series econometric models when applied to a small Spanish region. The variable of interest is the sectoral GVA of the Basque Country. The results support the use of causal models, which outperform univariate models, such as ARMA and SETAR, in forecasting accuracy. The use of a causal model, such as a simple Dynamic Regression model, offers a systematic advantage in the case of a small regional economy for which abundant regional statistical information is available.