HYBRID ESTIMATION FOR AN ERGODIC DIFFUSION PROCESS BASED ON REDUCED DATA - Collections

＜journal article＞
HYBRID ESTIMATION FOR AN ERGODIC DIFFUSION PROCESS BASED ON REDUCED DATA

Creator	Creator Name Kaino, Yusuke 貝野, 友祐カイノ, ユウスケ Affiliation Affiliation Name Graduate School of Engineering Science, Osaka University 大阪大学基礎工学部
	Creator Name Uchida, Masayuki 内田, 雅之ウチダ, マサユキ Affiliation Affiliation Name Graduate School of Engineering Science, Osaka University 大阪大学基礎工学部 Affiliation Affiliation Name Center for Mathematical Modeling and Data Science (MMDS), Osaka University Toyonaka
	Creator Name Yoshida, Yuto 吉田, 友土ヨシダ, ユウト Affiliation Affiliation Name Science Information Systems Co., Ltd.
Language	English
Publisher	Research Association of Statistical Sciences
Publisher	統計科学研究会
Date	2017-12
Source Title	Bulletin of informatics and cybernetics
Vol	49
First Page	89
Last Page	118
Publication Type	Version of Record
Access Rights	open access
Crossref DOI	https://doi.org/10.5109/2232332
Abstract	We consider efficient estimation of both drift and diffusion coefficient parameters for an ergodic diffusion process from discrete observations. From the viewpoint of numerical analysis, hybrid estima...tors based on the initial Bayes type estimators from the reduced data are proposed and the asymptotic properties of the hybrid estimators, including convergence of moments, are shown. Furthermore, we give examples and simulation results in order to investigate the asymptotic performance of the proposed estimators.show more

File	FileType	Size	Views	Description
7Kaino	pdf	198 KB	326

PISSN	0286-522X
EISSN	2435-743X
NCID	AA10634475
Record ID	2232332
Peer-Reviewed	Refereed
Subject Terms	Adaptive maximum likelihood type estimator
	Bayes type estimator
	convergence of moments
	high frequency data
	stochastic differential equation
Funding Information	Funder Name 日本学術振興会 Japan Society for the Promotion of Science Award Number 24300107 Award Title 確率微分方程式モデルの統計推測法の開発と高頻度データ解析への応用 Statistical inference for stochastic differential equations and its applications to high frequency data analysis
	Funder Name 日本学術振興会 Japan Society for the Promotion of Science Award Number 17H01100 Award Title 確率微分方程式モデルに基づく数理・データ科学とシミュレーション科学の融合的研究
	Funder Name 国立研究開発法人科学技術振興機構 JST CREST
Created Date	2019.04.23
Modified Date	2023.11.15