scientific article; zbMATH DE number 3903803
From MaRDI portal
Publication:3681786
[For the entire collection see Zbl 0549.00023.] This paper describes certain rather obvious algorithms for the estimation of ARMA orders from the estimated covariance sequence. It is well known that the Hankel matrix associated with an ARMA process has finite rank. Hence, a well known idea is to study the rank behaviour of the Hankel matrix constructed from the empirical autocorrelation function, and to decide the orders accordingly. Such a method is rather inefficient, however. The author seems to be unaware of the developments in this field.
Recommendations
Cited in
(12)- Convergence acceleration methods: The past decade
- The behaviour of the Lagrangian multiplier test in testing the orders of an ARMA-model
- Sequence transformations as statistical tools
- On estimating the order of an ARMA process
- Rational transfer function approximation (with discussion)
- The -algorithm for the identification of a transfer-function model: Some applications
- New method of order estimation for ARMA/ARMAX processes
- ON THE ASYMPTOTIC DISTRIBUTION OF THE GENERALIZED PARTIAL AUTOCORRELATION FUNCTION IN AUTOREGRESSIVE MOVING-AVERAGE PROCESSES
- scientific article; zbMATH DE number 3913498 (Why is no real title available?)
- ARMA order estimation via matrix perturbation theory
- scientific article; zbMATH DE number 1222390 (Why is no real title available?)
- On some simple, autoregression-based estimation and identification techniques for ARMA models
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3681786)