ISSN 0474-8662. Information Extraction and Processing. 2019. Issue 47 (123)
Home Back to issue

Systematic error of LSM-estimation of covariance components of biperiodically correlated random signals

Javorskyj I. M.
Karpenko Physico-Mechanical Institute of the NAS of Ukraine, Lviv
Telecommunication Institute of University of Technology and Life Science, Bydgoszcz, Poland
Dzeryn O. Y.
Karpenko Physico-Mechanical Institute of the NAS of Ukraine, Lviv
Yuzefovych R. M.
Karpenko Physico-Mechanical Institute of the NAS of Ukraine, Lviv
Lviv Polytechnic National University

https://doi.org/10.15407/vidbir2019.47.026

Keywords: biperiodically correlated random signal, least squares method, covariance component LSM-estimation, systematic error

Cite as: Javorskyj I. M., Dzeryn O. Y., Yuzefovych R. M. Systematic error of LSM-estimation of covariance components of biperiodically correlated random signals. Information Extraction and Processing. 2019, 47(123), 26-33. DOI:https://doi.org/10.15407/vidbir2019.47.026


Abstract

Systematic error of the LSM-estimation for the covariance components of periodically corre¬lated random signals (BPCRS) is analysed. It is show that this error is caused by the prelimi¬nary mean function estimation only. The formulae of the dependence of their error on the cova¬riance component is obtained and asymptotic unbiasedness of estimation is proved. The partial case of BPCRS is considered and comparison with component estimators is given.


References