On the uniqueness of prediction error models for systems with noisy input-output data (Q1821753)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: On the uniqueness of prediction error models for systems with noisy input-output data |
scientific article; zbMATH DE number 3999812
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | On the uniqueness of prediction error models for systems with noisy input-output data |
scientific article; zbMATH DE number 3999812 |
Statements
On the uniqueness of prediction error models for systems with noisy input-output data (English)
0 references
1987
0 references
This paper addresses the uniqueness problem of the prediction error (PE) identification for a class of linear systems with noisy input and output data. Necessary and sufficient conditions are derived for the corresponding PE loss function to have (asymptotically) a unique global minimum. The results indicate that a PE algorithm may give very bad parameter estimates for systems not satisfying these conditions. Such a possibility is illustrated by a numerical example. While the PE method is used as a vehicle for illustration, the derived conditions for global uniqueness (or identifiability) apply to any consistent estimation method based on second-order data.
0 references
system identification
0 references
global identifiability
0 references
noisy systems
0 references
prediction error
0 references
parameter estimates
0 references
0.86512154
0 references
0.8535328
0 references
0.84983027
0 references
0.8490665
0 references
0.8490015
0 references
0.8479025
0 references
0.84694695
0 references
