Estimation of Accuracy and Reliability of Models of φ-sub-Gaussian Stochastic Processes in Spaces
DOI:
https://doi.org/10.20535/1810-0546.2017.4.105428Keywords:
Stochastic processes, φ-sub-Gaussian processes, Models of stochastic processes, Reliability and accuracy of models of stochastic processesAbstract
Background. At present, in the theory of stochastic process modeling a problem of assessment of reliability and accuracy of stochastic process model in C(T) space wasn’t studied for the case of inexplicit decomposition of process in the form of a series with independent terms.
Objective. The goal is to study reliability and accuracy in C(T) of models of processes from Subφ(Ω) that cannot be decomposed in a series with independent elements explicitly.
Methods. Using previous research in the field of modeling of stochastic processes, assumption is considered about possibility of decomposition of a stochastic process in the series with independent elements that can be found using approximations.
Results. Impact of approximation error of process decomposition in series with independent elements on reliability and accuracy of modeling of stochastic process in C(T) is studied.
Conclusions. Theorems are proved that allow estimation of reliability and accuracy of a model in C(T) of a stochastic process from Subφ(Ω) in the case when decomposition of this process in a series with independent elements can be found only with some error, for example, using numerical approximations.
References
O.I. Vasylyk et al., φ-Sub-Gaussian Stochastic Processes. Kyiv, Ukraine: Kyiv University, 2008.
Yu.V. Kozachenko and I.V. Rozora, “Accuracy and reliability of models of stochastic processes of the space Subφ(Ω)”, Theor. Probab. Math. Statist., no. 71, pp. 105–117, 2005.
Yu. Kozachenko and N.V. Troshki, “Accuracy and reliability of a model of Gaussian random processes in C(T) space”, Int. J. Stat. Manag. Syst., vol. 10, no. 1-2, pp. 1–15, 2015.
Yu.V. Kozachenko and A.O. Pashko, Modeling of Stochastic Processes. Kyiv, Ukraine: Kyiv University, 1999.
O.M. Mokliachuk, “Simulation of random processes with known correlation function with the help of Karhunen–Loeve decomposition”, Theory of Stochastic Processes, iss. 13 (29), no. 4, pp. 90–94, 2007.
Yu.V. Kozachenko and O.M. Moklyachuk, “Sample continuity and modeling of stochastic processes from the spaces DV,W”, Theor. Probab. Math. Statist., no 83, pp. 95–110, 2011.
O.M. Moklyachuk, “Models with given reliability and accuracy in Lp(T) of stochastic processes from Subφ(Ω) that can be represented in series with independent elements”, Prykladna Statystyka. Aktuarna ta Finansova Matematyka, no. 2, pp. 24–29, 2012 (in Ukrainian).
O. Mokliachuk, “Modeling of stochastic processes in Lp(T) using orthogonal polynomials”, Universal J. Appl. Math., vol. 2, pp. 141–147, 2014. doi: 10.13189/ujam.2014.020304
V.V. Buldygin and Yu.V. Kozachenko, Metric Characterization of Random Variables and Random Processes (Trans. Math. Monographs, vol. 188). Providence,RI: AMS, American Mathematical Society, XII, 2000.
Yu.V. Kozachenko and E.I. Ostrovskij, “Banach spaces of random variables of sub-Gaussian type”, Theor. Probab. Math. Statist., no. 32, pp. 45–56, 1986.
Downloads
Published
Issue
Section
License
Copyright (c) 2017 Igor Sikorsky Kyiv Polytechnic Institute
This work is licensed under a Creative Commons Attribution 4.0 International License.
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
