Parameter estimation via homogenization for stochastic dynamical systems with oscillating coefficients

Autor:	Yanjie Zhang, Xinyong Zhang, Haokun Lin, Hui Wang
Rok vydání:	2018
Předmět:	010104 statistics & probability Mathematical optimization Dynamical systems theory Estimation theory Modeling and Simulation 010102 general mathematics Statistical physics 0101 mathematics 01 natural sciences Homogenization (chemistry) Mathematics
Zdroj:	Stochastics and Dynamics. 18:1850025
ISSN:	1793-6799 0219-4937
DOI:	10.1142/s0219493718500259
Popis:	This paper is devoted to studying parameter estimation for a class of stochastic dynamical systems with oscillating coefficients. We show that the homogenized systems faithfully capture the dynamical quantities such as mean exit time and escape probability. Exacting data from observations on the mean exit time (or escape probability) of the original systems, we try to fit the mean exit time (or escape probability) of the homogenized systems by least square method. In this way, we can accurately estimate the unknown parameter in the drift under appropriate assumptions. Furthermore, we conduct some numerical experiments to illustrate our method.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4368ff666c445bc22a03865f66e820a2 https://doi.org/10.1142/s0219493718500259 Zobrazit plný text záznamu