Autori: P.C. Logofatu, D. Apostol

Editorial: Measurement, 41, p.1100-1104, 2008.

Rezumat:

A new, fully statistical approach for regression analysis is presented and used for deriving the formula for the estimation error of the parameters of the fit and the associated joint confidence levels and limits. The key feature of the approach consists in two complementary parameterizations of the error space that are equivalent to a change of coordinates. This feature makes possible all the derivations and gives a marked statistical character to the approach. This study is intended for graduate students in physics and any physicist with an interest in regression analysis. Although this approach is more lengthy and laborious than the usual one, it has the advantage that it follows step by step all the intricacies, statistical and topological, of the regression analysis, and the final formulae do not appear as black boxes to be used such as they are, but all their components have established meanings.

Cuvinte cheie: analiza de eroare, metoda de fitare a celor mai mici patrate, probabilitate // error analysis, least squares fit, probability

URL: http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V42-4S2F5JN-1&_user=8487703&_coverDate=12%2F31%2F2008&_rdoc=4&_fmt=high&_orig=browse&_srch=doc-info(%23toc%235746%232008%23999589989%23701498%23FLA%23display%23Volume)&_cdi=5746&_sort=d&_docanchor