Algorithms for global total least squares modelling of finite multivariable time series (Q1892997): Difference between revisions
From MaRDI portal
Latest revision as of 08:30, 30 July 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Algorithms for global total least squares modelling of finite multivariable time series |
scientific article |
Statements
Algorithms for global total least squares modelling of finite multivariable time series (English)
0 references
9 November 1995
0 references
This paper presents several algorithms related to the global total least squares (GTLS) modelling of multivariable time series observed in a finite time interval. Necessary conditions for optimality are described in terms of state space representations. A Gauss-Newton method for the construction of GTLS models is presented. An example illustrates the results.
0 references
identification
0 references
linear systems
0 references
Kalman filters
0 references
global total least squares
0 references
modelling
0 references
time series
0 references
state space
0 references
Gauss-Newton method
0 references
time-invariant
0 references
