On the accuracy of total least squares and least squares techniques in the presence of errors on all data

✍ Scribed by Sabine Van Huffel; Joos Vandewalle

• Publisher: Elsevier Science
• Year: 1989
• Tongue: English
• Weight: 388 KB
• Volume: 25
• Category: Article
• ISSN: 0005-1098
• DOI: 10.1016/0005-1098(89)90033-2

✦ Synopsis

Abstroct~Every linear parameter estimation problem gives rise to an overdetermined set of linear equations AX ~ B which is usually solved with the ordinary least squares (LS) method. Often, both A and B are inaccurate. For these cases, a more general fitting technique, called total least squares (TLS), is devised. This paper investigates, via simulations how perturbations on both A and B affect the accuracy of the TLS and LS solution. Several important factors are discussed, as well as the consistency properties of the TLS solution in the presence of uncorrelated and equally sized errors. *