No Cover Image

Journal article 536 views

A forecasting procedure for nonlinear autoregressive time series models / Yuzhi Cai

Journal of Forecasting, Volume: 24

Swansea University Author: Yuzhi, Cai

Abstract

Forecasting for nonlinear time series is an important topic intime series analysis. Existing numerical algorithms for multi-stepahead forecasting ignore accuracy checking, alternative MonteCarlo methods are also computationally very demanding and itsaccuracy is difficult to control too. In this pape...

Full description

Published in: Journal of Forecasting
Published: 2005
URI: https://cronfa.swan.ac.uk/Record/cronfa15295
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Forecasting for nonlinear time series is an important topic intime series analysis. Existing numerical algorithms for multi-stepahead forecasting ignore accuracy checking, alternative MonteCarlo methods are also computationally very demanding and itsaccuracy is difficult to control too. In this paper a numericalforecasting procedure for nonlinear autoregressive time seriesmodels is proposed.The forecasting procedure can be used to obtain approximate \(m\)-step ahead predictiveprobability density function, predictive distribution function, predictive mean and variance etc. for a range of nonlinearautoregressive time series models. Examples in the paper showthat the forecasting procedure works very well both in theaccuracy of the results and in the ability of dealing withdifferent nonlinear autoregressive time series models.
Keywords: Chapman-Kolmogorov equation; Forecasting procedure; Nonlinear autoregressive Time series.
College: School of Management
End Page: 351