Asymptotic Unbiasedness and Consistency of Cross-Correlogram Estimators of Response Functions in Linear Continuous Systems
DOI:
https://doi.org/10.20535/1810-0546.2014.4.28208Keywords:
Response function, Sample cross-correlogram, Unbiasedness, Consistency, The Young inequality for convolutionsAbstract
The estimation problem of an unknown real-valued response function of a linear continuous system is considered. We suppose that a family of zero-mean stationary Gaussian processes, which are close, in some sense, to a white noise, disturbs the system. Integral-type sample input-output cross-correlograms are taken as estimators of the response function from \begin{equation}L_{2}\left(\mathbb{R}\right)\end{equation}. The corresponding cross-correlogram estimator depends on two parameters (a parameter of a scheme of series and a length of an averaging interval) and is biased. Our aim is to investigate the properties of asymptotic unbiasedness and consistency of the estimator. The main results are obtained due to additional assumptions about the uniform Lipschitz condition for the response function, and balance conditions between the correlation functions of inputs and the parameter of the scheme of series. Properties of the Fourier transform, some properties of Fejers kernels and the Young inequality for convolutions are used to prove these facts. Both asymptotic unbiasedness and consistency in mean square sense are studied in the paper.References
Бендат Дж., Пирсол А. Применения корреляционного и спектрального анализа. – М.: Мир, 1983. – 312 с.
V.V. Buldygin and Fu Li, “On asymptotical normality of an estimation of unit impulse responses of linear systems” (I, II), Theor. Probab. and Math. Statist., vol. 54, pp. 17–24, 1997; vol. 55, pp. 29–36, 1997.
Булдыгин В.В., Козаченко Ю.В., Метрические характеристики случайных величин и процессов. – К.: ТВіМС, 1998. – 290 с.
V.V. Buldygin and V.G. Kurotschka, “On cross-correlogram estimators of the response function in continuous linear systems from discrete observations”, Random Oper. and Stoch. Eq., vol. 7, no. 1, pp. 71–90, 1999.
V. Buldygin et al., “Asymptotic normality of cross-correlogram estimates of the response function”, Statistical Interference for Stochastic Proc., vol. 7, pp. 1–34, 2004.
Булдигін В.В., Блажієвська І.П. Про кореляційні властивості корелограмних оцінок імпульсних перехідних функцій // Наукові вісті НТУУ “КПІ”. – 2009. – № 5. – С. 120–128.
Булдигін В.В., Блажієвська І.П. Асимптотичні властивості корелограмних оцінок імпульсних перехідних функцій лінійних систем // Наукові вісті НТУУ “КПІ”. – 2010. – № 4. – С. 16–27.
M. Schetzen, The Volterra and Wiener Theories of Nonlinear Systems. New York: Wiley, 1980, 618 р.
I.P. Blazhievska, “Correlogram estimation of response functions of linear systems in scheme of some independent samples”, Theory of Stochastic Proc., vol. 17 (33), no. 1, pр. 16–27, 2011.
Колмогоров А.Н., Фомин С.В. Элементы теории функций и функционального анализа. – М.: Наука, 1976. – 544 с.
R.E. Edwards, Functional analysis: theory and applications. New York: Holt, Rinehart and Winston, 1965, 798 р.
Downloads
Published
Issue
Section
License
Copyright (c) 2017 NTUU KPI Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
