Nonlinear forecasting using nonparametric transfer function models
Part of : WSEAS transactions on business and economics ; Vol.6, No.5, 2009, pages 209-218
Issue:
Pages:
209-218
Author:
Abstract:
The focus of this paper is using nonparametric transfer function models in forecasting. Nonparametricsmoothing methods are used to model the relationship between variables (the transfer function) and the noise ismodeled as an Autoregressive Moving Average (ARMA) process. The transfer function is estimated jointly withthe ARMA parameters. Nonparametric smoothing methods are flexible thus can be used to model highly nonlinearrelationships between variables. In this paper polynomial splines are used to model the transfer function. Modelingnoise term as an ARMA process removes the serial correlation so the transfer function can be estimated efficiently.As a result, the nonparametric transfer function model can generate accurate forecasts when the transfer function ishighly nonlinear with unknown functional form. The proposed polynomial splines-based estimator is also highlycomputationally efficient. The performance of nonparametric transfer function models is demonstrated in thispaper by forecasting river flow based on temperature and precipitation. A comparison of the results show that theperformance of this model is better than some widely accepted benchmark models.
Subject:
Subject (LC):
Keywords:
nonparametric smoothing, time series, forecast
Notes:
Περιέχει γραφήματα, πίνακες και βιβλιογραφία
