Nonlinear time series models have become fashionable tools to describe and forecast a variety of economic time series. A closer look at reported empirical studies, however, reveals that these models apparently fit well in-sample, but rarely show a substantial improvement in out-of-sample forecasts, at least over linear models. One of the many possible reasons for this finding is that inappropriate model selection criteria and forecast evaluation criteria are used. In this paper we therefore propose a novel criterion, which we believe does more justice to the very nature of nonlinear models. Simulations show that our criterion outperforms currently used criteria, in the sense that the true nonlinear model is more often found to perform better in out-of-sample forecasting than a benchmark linear model. An empirical illustration for US GDP emphasizes its relevance.

Additional Metadata
Keywords forecast evaluation, forecasting, model selection, nonlinearity
JEL Time-Series Models; Dynamic Quantile Regressions (jel C22), Model Evaluation and Testing (jel C52), Forecasting and Other Model Applications (jel C53), Business Fluctuations; Cycles (jel E32), Forecasting and Simulation (jel E37)
Persistent URL
Series Econometric Institute Research Papers
van Dijk, D.J.C, & Franses, Ph.H.B.F. (2003). Selecting a Nonlinear Time Series Model using Weighted Tests of Equal Forecast Accuracy (No. EI 2003-10). Econometric Institute Research Papers. Retrieved from