The Extended STLS Algorithm for Minimizing the Extended LS Criterion

Arie Yeredor ()
Additional contact information
Arie Yeredor: Tel-Aviv University, Dept. of Elect. Eng. — Systems

A chapter in Total Least Squares and Errors-in-Variables Modeling, 2002, pp 107-117 from Springer

Abstract: Abstract The recently-introduced Extended Least-Squares (XLS) parameters — estimation criterion is aimed at discriminating measurement errors from modelling errors (or “misfit” from “latency” errors). Using versatile weighting of “presumed errors”, it encompasses the classical Least-Squares (LS) criterion on one hand, and the (Structured, or Constrained) Total LS [(S,C)TLS] criteria on the other hand. Thus, the STLS algorithm, originally aimed at solving TLS problems with structural constraints, can be modified, or “extended”, to solve the XLS minimization problem. In this paper we introduce the Extended STLS algorithm, and demonstrate its use in the XLS context with estimating the parameters of a noisy Auto-Regressive (AR) process. We briefly compare the Extended STLS algorithm to other algorithms serving the same purpose.

Keywords: extended least squares (XLS); structured total least squares (STLS); extended STLS (ESTLS); system identification; latency error. (search for similar items in EconPapers)
Date: 2002
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-94-017-3552-0_10

Ordering information: This item can be ordered from
http://www.springer.com/9789401735520

DOI: 10.1007/978-94-017-3552-0_10

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().