Semiparametric ARX neural-network models with an application to forecasting inflation

We examine semiparametric nonlinear autoregressive models with exogenous variables (NLARX) via three classes of artificial neural networks: the first one uses smooth sigmoid activation functions; the second one uses radial basis activation functions; and the third one uses ridgelet activation functions. We provide root mean squared error convergence rates for these ANN estimators of the conditional mean and median functions with stationary beta-mixing data. As an empirical application, we compare the forecasting performance of linear and semiparametric NLARX models of US inflation. We find that all of our semiparametric models outperform a benchmark linear model based on various forecast performance measures. In addition, a semiparametric ridgelet NLARX model which includes various lags of historical inflation and the GDP gap is best in terms of both forecast mean squared error and forecast mean absolute deviation error.

[1]  Eric Ghysels,et al.  Can we improve the perceived quality of economic forecasts , 2001 .

[2]  Norman R. Swanson,et al.  A Model-Selection Approach to Assessing the Information in the Term Structure Using Linear Models and Artificial Neural Networks , 1995 .

[3]  Federico Girosi,et al.  Regularization Theory, Radial Basis Functions and Networks , 1994 .

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[5]  Federico Girosi,et al.  On the Relationship between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions , 1996, Neural Computation.

[6]  Kurt Hornik,et al.  Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives , 1994, Neural Computation.

[7]  Xiaotong Shen,et al.  Sieve extremum estimates for weakly dependent data , 1998 .

[8]  Halbert White,et al.  Improved Rates and Asymptotic Normality for Nonparametric Neural Network Estimators , 1999, IEEE Trans. Inf. Theory.

[9]  Richard G. Lipsey,et al.  The Relation between Unemployment and the Rate of Change of Money Wage Rates in the United Kingdom , 1960 .

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[11]  H. Bierens.  Model-free Asymptotically Best Forecasting of Stationary Economic Time Series , 1990, Econometric Theory.

[12]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[13]  A. W. Phillips,et al.  A. W. H. Phillips: Collected Works in Contemporary Perspective: The relation between unemployment and the rate of change of money wage rates in the United Kingdom, 1861-1957 , 2000 .

[14]  Carlo Novara,et al.  Nonlinear Time Series , 2003 .

[15]  C. Granger,et al.  Modelling Nonlinear Economic Relationships , 1995 .

[16]  P. Phillips.  Testing for a Unit Root in Time Series Regression , 1988 .

[17]  Daniel F. McCaffrey,et al.  Convergence rates for single hidden layer feedforward networks , 1994, Neural Networks.

[18]  Dharmendra S. Modha,et al.  Minimum complexity regression estimation with weakly dependent observations , 1996, IEEE Trans. Inf. Theory.

[19]  Y. Meyer.  Wavelets and Operators , 1993 .

[20]  Andrew T. Levin,et al.  Inferences from Parametric and Non-Parametric Covariance Matrix Estimation Procedures , 1995 .

[21]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[22]  P. Doukhan.  Mixing: Properties and Examples , 1994 .

[23]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[24]  T. Sargent.  The Conquest of American Inflation , 1999 .

[25]  H. White.  Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models , 1989 .

[26]  C. J. Stone,et al.  Optimal Global Rates of Convergence for Nonparametric Regression , 1982 .

[27]  Norman R. Swanson,et al.  A Model Selection Approach to Real-Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks , 1997, Review of Economics and Statistics.

[28]  Clive W. J. Granger,et al.  Testing for neglected nonlinearity in time series models: A comparison of neural network methods and alternative tests , 1993 .

[29]  W. Fuller,et al.  Distribution of the Estimators for Autoregressive Time Series with a Unit Root , 1979 .

[30]  E. Candès.  Harmonic Analysis of Neural Networks , 1999 .

[31]  Y. Makovoz.  Random Approximants and Neural Networks , 1996 .

[32]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[33]  Jeffrey S. Racine.  On the Nonlinear Predictability of Stock Returns Using Financial and Economic Variables , 2001 .