Combined forecasts from a linear and a nonlinear model areinvestigated for timeseries with possibly nonlinear characteristics. The forecasts arecombined by aconstant coefficient regression method as well as a time varyingmethod. Thetime varying method allows for a locally (non)linear model....

Pure time series-based tests fail to find empirical support formonetary exchange rate models. In this paper we apply pooled timeseries estimation on a forward-looking monetary model, resulting inparameter estimates which are in compliance with the underlyingtheory. Based on a panel version of...

In this paper, we make use of state space models to investigate the presence of stochastic trends in economic time series. A model is specified where such a trend can enter either in the autoregressive representation or in a separate state equation. Tests based on the former are analogous to...

In this paper we introduce the STAR-STGARCH model that can characterizenonlinear behaviour both in the conditional mean and the conditionalvariance. A modelling cycle for this family of models, consisting ofspecification, estimation, and evaluation stages is constructed.Misspecification tests...

We advocate the use of absolute moment ratio statistics in conjunctionwith standard variance ratio statistics in order to disentangle lineardependence, non-linear dependence, and leptokurtosis in financial timeseries. Both statistics are computed for multiple return horizonssimultaneously, and...

This paper suggests a unified framework for testing the adequacy of anestimated GARCH model. Nothing more complicated than standard asymptotictheory is required. Parametric tests of no ARCH in standardized errors,symmetry, and parameter constancy are suggested. Estimating the alternativewhen the...

A major problem in applying neural networks is specifying the sizeof the network. Even for moderately sized networks the number ofparameters may become large compared to the number of data. In thispaper network performance is examined while reducing the size of thenetwork through the use of...

A key application of long memory time series models concerns inflation. Long memory implies that shocks have a long-lasting effect. It may however be that empirical evidence for long memory is caused by neglecting one or more level shifts. Since such level shifts are not unlikely for inflation,...