Estimation of Measurand Parameters for Data from Asymmetric Distributions by Polynomial Maximization Method
No Thumbnail Available
Date
2018
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Nature
Abstract
In this paper the non-conventional method for evaluating the standard uncertainty of the estimator of measurand value obtained from the non-Gaussian asymmetrically distributed sampled data with a priori partial description (known only few initial moments, unknown PDF distribution of population) is proposed. This method of statistical estimation is based on the apparatus of maximization the stochastic polynomials (PMM method proposed by Kunchenko) and uses the higher-order statistics (moment or cumulant description) of random variables. The analytical expressions for finding estimates and analyzing their accuracy to the degree of the polynomial s = 2 is given. It is shown that for the asymmetric PDF-s the uncertainty estimates for received polynomial are generally smaller than the uncertainty estimates obtained based on the mean (arithmetic average). Reducing the uncertainty of measurement depends on the skewness and kurtosis. On the basis of the Monte Carlo method statistical modelling is carried out, the results confirm the effectiveness of the proposed approach.
Description
Keywords
SOCIAL SCIENCES::Statistics, computer and systems science
Citation
Warsza, Z. L., Zabolotnii, S. V. Estimation of Measurand Parameters for Data from Asymmetric Distributions by Polynomial Maximization Method. In: Szewczyk, R., Zieliński, C., Kaliczyńska, M. (eds) Automation 2018. Advances in Intelligent Systems and Computing. Springer, Cham. 2018. vol. 743. рр. 746-757. https://doi.org/10.1007/978-3-319-77179-3_74.