A Simple Variable Selection Technique for Nonlinear Models

Rech, Gianluigi; Teräsvirta, Timo; Tschernig, Rolf

doi:10.1081/sta-100104360

Cited by 53 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that by following this procedure, the variables for the whole NN model are selected at the same time. Rech et al (2001) showed that the procedure works well already in small samples when compared to well-known nonparametric techniques. Furthermore, it can be applied successfully even in large samples when nonparametric model selection becomes computationally infeasible.…”

Section: Variable Selectionmentioning

confidence: 97%

Building neural network models for time series: a statistical approach

2005

Self Cite

View full text Add to dashboard Cite

This paper is concerned with modelling time series by single hidden layer feedforward neural network models. A coherent modelling strategy based on statistical inference is presented. Variable selection is carried out using simple existing techniques. The problem of selecting the number of hidden units is solved by sequentially applying Lagrange multiplier type tests, with the aim of avoiding the estimation of unidentified models. Misspecification tests are derived for evaluating an estimated neural network model. All the tests are entirely based on auxiliary regressions and are easily implemented. A small-sample simulation experiment is carried out to show how the proposed modelling strategy works and how the misspecification tests behave in small samples. Two applications to real time series, one univariate and the other multivariate, are considered as well. Sets of one-step-ahead forecasts are constructed and forecast accuracy is compared with that of other nonlinear models applied to the same series. Copyright © 2006 John Wiley & Sons, Ltd.

show abstract

Section: Variable Selectionmentioning

confidence: 97%

Building neural network models for time series: a statistical approach

2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…The combination of variables is chosen to yield the lowest value of the MSC. Rech et al (2001) showed that the procedure works well in small samples when compared with well known nonparametric techniques. Furthermore, the procedure can be applied successfully even in large samples when nonparametric model selection is not computationally feasible.…”

Section: Model Selectionmentioning

confidence: 97%

“…However, as noted in Pitarakis (2006), this method may have an adverse effect on the final model specification. An alternative approach, which is adopted here, is to consider a k-th order polynomial approximation to the nonlinear component of the DGP, as proposed in Rech et al (2001), and applied with success in Medeiros et al (2006), Medeiros and Veiga (2005), and SuarezFariñas et al (2004). As the logistic functions in (5) depend only on the scalar variable z t , the polynomial approximation can be simplified dramatically as follows 3 :…”

Section: Model Selectionmentioning

confidence: 99%

A multiple regime smooth transition Heterogeneous Autoregressive model for long memory and asymmetries

McAleer

Medeiros

2008

Journal of Econometrics

146

View full text Add to dashboard Cite

a b s t r a c tIn this paper we propose a flexible model to describe nonlinearities and long-range dependence in time series dynamics. The new model is a multiple regime smooth transition extension of the Heterogeneous Autoregressive (HAR) model, which is specifically designed to model the behavior of the volatility inherent in financial time series. The model is able to simultaneously approximate long memory behavior, as well as describe sign and size asymmetries. A sequence of tests is developed to determine the number of regimes, and an estimation and testing procedure is presented. Monte Carlo simulations evaluate the finite-sample properties of the proposed tests and estimation procedures. We apply the model to several Dow Jones Industrial Average index stocks using transaction level data from the Trades and Quotes database that covers ten years of data. We find strong support for long memory and both sign and size asymmetries. Furthermore, the new model, when combined with the linear HAR model, is viable and flexible for purposes of forecasting volatility.

show abstract

“…They are also available in large samples where the computational burden of nonparametric techniques becomes prohibitive. Rech, Teräsvirta, and Tschernig (2001) applied this idea to nonlinear variable selection.…”

Section: Introductionmentioning

confidence: 99%

Testing the Granger Noncausality Hypothesis in Stationary Nonlinear Models of Unknown Functional Form

Péguin-Feissolle¹,

Strikholm²,

Teräsvirta³

2013

Communications in Statistics - Simulation and Computation

Self Cite

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may January 2012Abstract In this paper we propose a general method for testing the Granger noncausality hypothesis in stationary nonlinear models of unknown functional form. These tests are based on a Taylor expansion of the nonlinear model around a given point in the sample space. We study the performance of our tests by a Monte Carlo experiment and compare these to the most widely used linear test. Our tests appear to be well-sized and have reasonably good power properties.

show abstract

A Simple Variable Selection Technique for Nonlinear Models

Cited by 53 publications

References 15 publications

Building neural network models for time series: a statistical approach

Building neural network models for time series: a statistical approach

A multiple regime smooth transition Heterogeneous Autoregressive model for long memory and asymmetries

Testing the Granger Noncausality Hypothesis in Stationary Nonlinear Models of Unknown Functional Form

Contact Info

Product

Resources

About