Derivation of ARMA parameters and orders from pure AR models
- 1 February 1975
- journal article
- research article
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 6 (2), 101-106
- https://doi.org/10.1080/00207727508941799
Abstract
The paper describes a consistent and sequential method for estimating the orders and parameters of mixed autoregressivu-moving-average (ARMA) processes. The method is based on employing sequential least squares estimates of pure autoregressive (AR) models.Keywords
This publication has 3 references indexed in Scilit:
- Identification of predictor and filter parameters by ARMA methods†International Journal of Control, 1973
- On-line identification of linear dynamic systems with applications to Kalman filteringIEEE Transactions on Automatic Control, 1971
- On the Statistical Treatment of Linear Stochastic Difference EquationsEconometrica, 1943