Theory of Bilinear Time Series Models
Author:
- 1 January 1985
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 14 (10) , 2549-2561
Abstract
In this paper, we prove some theoretic properties of bilinear time series models which are extension of ARMA models. The sufficient conditions for asymptotic stationarity and ivertibility of some types of bilinear models are derived. The structural theory of discussed bilinear models is similar to that of ARMA models. For illustration, a bilinear model has been fitted to the Wolfer sunspot numbers and a substantial reduction in sum of squared residuals is obtained as comparing with Box-Jenkins ARMA model.Keywords
This publication has 5 references indexed in Scilit:
- A note on bilinear time series modelsStochastic Processes and their Applications, 1982
- Stationarity and invertibility of simple bilinear modelsStochastic Processes and their Applications, 1982
- On the Theory of Bilinear Time Series ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1981
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- Multiple Time Series1970