Szczegóły publikacji
Opis bibliograficzny
Application of effective number of observations and effective degrees of freedom for analysis of autocorrelated observations / A. ZIĘBA // W: Advanced mathematical and computational tools in metrology and testing X : [10th International Conference on Advanced Mathematical and Computational Tools in Metrology and Testing (AMCTM) : St Petersburg, Russia : September 09-11, 2014] / ed. F. Pavese, [et al.]. — Singapore : World Scientific Publishing Co. Pte. Ltd., cop. 2015. — (Series on Advances in Mathematics for Applied Sciences ; ISSN 1793-0901 ; vol. 86). — ISBN: 978-981-4678-61-2. — S. 417–424. — Bibliogr. s. 423–424
Autor
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 95546 |
|---|---|
| Data dodania do BaDAP | 2016-02-08 |
| Rok publikacji | 2015 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | 10th International Conference on Advanced Mathematical and Computational Tools in Metrology and Testing |
| Czasopismo/seria | Series on Advances in Mathematics for Applied Sciences |
Abstract
The minimum extension to the standard formalism of Type A uncertainty evaluation for autocorrelated observations consists in retaining the arithmetic mean as an estimator of expected value but changing the formulae for sample standard deviation, standard deviation of the mean and coverage interval. These formulae can be expressed in a compact form by introducing two quantities: the effective number of observations n(eff) and the effective degrees of freedom n(eff). They are fixed real numbers when the autocorrelation function is known and they become estimators when only an estimate of the autocorrelation function is available. The presentation of the subject involves a critical synthesis of available solutions, augmented by some new results and tested using a Monte Carlo method.0.56