Applying nonparametric variable selection criteria in nonlinear regression models generally requires a substantial computational effort if the data set is large. In this paper we present a selection technique that is computationally much less demanding and performs well in comparison with...

The performance of analog forecasts is sensitive to the selection procedure of analogs from the history of observed time series. A method is presented to iteratively reduce a user-defined forecast error measure by adapting suitable metric weights for the components of the reconstructed states to...

This paper shows how a simple univariate stationary nonlinear process has an autocorrelation function suggesting that the underlying process has a long memory, although that is not the case. The conclusion is that just considering linear properties of a process may be misleading.

In this paper a unified framework for testing the adequacy of an estimated GARCH model is presented. Parametric LM or LM type tests of no ARCH in standardized errors, linearity, and parameter constancy are proposed. The asymptotic null distributions of the tests are standard, which makes...

While there has been a great deal of interest in the modelling of non-linearities in economic time series, there is no clear consensus regarding the forecasting abilities of non-linear time-series models. We evaluate the performance of two leading non-linear models in forecasting post-war US...

The local asymptotic normality for a class of generalized random coefficient autoregressive processes is established. This property implies the asymptotic optimality of the maximum likelihood estimator and the related test statistics. The model includes standard random coefficient autoregressive...

This paper examines the power properties of several linearity tests applied in time-series analysis. The tests are the ones Lee et al.(1993) used in their Monte Carlo study. The main tool used for power comparisons in this paper is the Pitman asymptotic relative efficiency. The results generally...