𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Comments on ‘non-convergence of the approximate maximum likelihood identification algorithm’

✍ Scribed by Lennart Ljung

Publisher
Elsevier Science
Year
1980
Tongue
English
Weight
130 KB
Volume
16
Category
Article
ISSN
0005-1098

No coin nor oath required. For personal study only.

✦ Synopsis

The following three comments and claims are made:

  1. The 'approximate maximum likelihood method ' [called RELS in (S6derstr6m et al., 1978)] may work well in applications even though it has been proven that it does not always converge.

  2. It was incorrect in (* Ljung et al., 1975) to call the 'simplifying assumption' to neglect the 0-dependence of the past residuals an 'assertion'.

  3. The asymptotic behaviour of the implemented algorithm will not be described by the differential equation theory of (Ljung, 1977) due to round off errors in the computer.

I shall comment on these claims separately.

📜 SIMILAR VOLUMES

Non-convergence of the approximate maxim
Non-convergence of the approximate maximum likelihood identification algorithm
✍ V. Panuska 📂 Article 📅 1980 🏛 Elsevier Science 🌐 English ⚖ 205 KB

The question of non-convergence of the approximate maximum likelihood identification algorithm is discussed. It is pointed out that although there are systems for which in theory the algorithm does not converge to any finite limit, the computer implementation always gives results which settle at con

On the uniqueness of maximum likelihood
On the uniqueness of maximum likelihood identification
✍ T Söderström 📂 Article 📅 1975 🏛 Elsevier Science 🌐 English ⚖ 426 KB

The maximum likelihood method of identification is a powerful tool for obtaining mathematical models of dynamic processes. To apply this method a loss function has to be minimized. The aim of the paper is an investigation of the local minimum points of this loss function for a common structure of a

On non-parametric maximum likelihood est
On non-parametric maximum likelihood estimation of the bivariate survivor function
✍ Ross L. Prentice 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 171 KB 👁 2 views

The likelihood function for the bivariate survivor function F, under independent censorship, is maximized to obtain a non-parametric maximum likelihood estimator F K . F K may or may not be unique depending on the con"guration of singly-and doubly-censored pairs. The likelihood function can be maxim

ON THE CONVERGENCE OF ZERO-FINDING EIGEN
ON THE CONVERGENCE OF ZERO-FINDING EIGENSOLUTION ALGORITHMS FOR SOLVING NON-LINEAR EIGENVALUE PROBLEMS
✍ MOHAMMEDI R. ABDEL-AZIZ 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 118 KB 👁 2 views

This paper presents a convergence theory for non-linear eigenvalue methods. The basic idea of these methods, which have been described by the author in an earlier paper, 1 is to apply an eigen-solver in conjunction with a zero-ÿnding technique for solving the non-linear eigenvalue problems. The main

COMMENTS ON “IDENTIFICATION OF MULTI-DEG
COMMENTS ON “IDENTIFICATION OF MULTI-DEGREE-OF-FREEDOM NON-LINEAR SYSTEMS UNDER RANDOM EXCITATIONS BY THE ‘REVERSE PATH’ SPECTRAL METHOD”
✍ J.A. FITZPATRICK; H.J. RICE 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 65 KB

The authors of reference [1] are to be commended for implementing the &&reverse path'' non-linear spectral analysis method for identifying the constituents elements of simulated three-and "ve-degree-of-freedom (d.o.f.) non-linear systems. However, we feel that the paper requires some comment as to o