A Bootstrap Artificial Neural Network Based Heterogeneous Panel Unit Root Test in Case of Cross Sectional Independence

This paper extends an inference test proposed in [1]. The seminal paper proposes an artificial neural network (ANN) based panel unit root test in a dynamic heterogeneous panel context. The ANN is not complex, but it is not necessarily in the aim of modeling macroeconomic time series. However, it is applied in a difficult mathematical context, in which the classical Gaussian asymptotic probabilistic theory does not apply. Some asymptotic properties for the test were set, however, the small sample properties are not satisfactory. Consequently, in this paper, we propose to use the simulation based numerical method named "bootstrap" to compute the small sample distribution of the test statistics. An application to a panel of bilateral real exchange rate series with the US Dollar from the 20 major OECD countries is provided.

[1]  David H. Papell,et al.  The purchasing power parity persistence paradigm , 2000 .

[2]  Robert L. Taylor,et al.  Boot-strapping unstable rst-order autoregressive processes , 1991 .

[3]  George Kapetanios,et al.  Testing for a Linear Unit Root against Nonlinear Threshold Stationarity , 2000 .

[4]  David H. Papell,et al.  The purchasing power parity puzzle is worse than you think , 2005 .

[5]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[6]  Philippe Jorion,et al.  Purchasing Power Parity in the Long Run , 1990 .

[7]  A. Walden,et al.  The Econometric Modelling of Financial Time Series. , 1995 .

[8]  M. Hashem Pesaran,et al.  A floor and ceiling model of US output , 1997 .

[9]  Mario Cerrato,et al.  A bootstrap panel unit root test under cross-sectional dependence, with an application to PPP , 2007, Comput. Stat. Data Anal..

[10]  George Kapetanios,et al.  Pure Significance Tests of the Unit Root Hypothesis Against Nonlinear Alternatives , 2003 .

[11]  George Kapetanios,et al.  A radial basis function artificial neural network test for neglected nonlinearity , 2003 .

[12]  Mario Cerrato,et al.  A Nonlinear Panel Unit Root Test under Cross Section Dependence , 2011 .

[13]  George Kapetanios,et al.  A Radial Basis Function Artificial Neural Network Test for ARCH , 2000 .

[14]  Bruce E. Hansen,et al.  Threshold Autoregressions with a Near Unit Root , 1998 .

[15]  A. Lo,et al.  THE ECONOMETRICS OF FINANCIAL MARKETS , 1996, Macroeconomic Dynamics.

[16]  George Kapetanios,et al.  Testing for a unit root in the nonlinear STAR framework , 2003 .

[17]  M. Pesaran,et al.  Testing for unit roots in heterogeneous panels , 2003 .

[18]  Mario Cerrato,et al.  An artificial neural network based heterogeneous panel unit root test in case of cross sectional independence , 2009, 2009 International Joint Conference on Neural Networks.