Home > Research > Publications & Outputs > Parameter inference for degenerate diffusion pr...

Links

Text available via DOI:

View graph of relations

Parameter inference for degenerate diffusion processes

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Parameter inference for degenerate diffusion processes. / Iguchi, Y.; Beskos, A.; Graham, Matthew .
In: Stochastic Processes and their Applications, Vol. 174, 104384, 31.08.2024.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Iguchi, Y, Beskos, A & Graham, M 2024, 'Parameter inference for degenerate diffusion processes', Stochastic Processes and their Applications, vol. 174, 104384. https://doi.org/10.1016/j.spa.2024.104384

APA

Iguchi, Y., Beskos, A., & Graham, M. (2024). Parameter inference for degenerate diffusion processes. Stochastic Processes and their Applications, 174, Article 104384. https://doi.org/10.1016/j.spa.2024.104384

Vancouver

Iguchi Y, Beskos A, Graham M. Parameter inference for degenerate diffusion processes. Stochastic Processes and their Applications. 2024 Aug 31;174:104384. Epub 2024 May 24. doi: 10.1016/j.spa.2024.104384

Author

Iguchi, Y. ; Beskos, A. ; Graham, Matthew . / Parameter inference for degenerate diffusion processes. In: Stochastic Processes and their Applications. 2024 ; Vol. 174.

Bibtex

@article{d2da4442573241aead19e67494401391,
title = "Parameter inference for degenerate diffusion processes",
abstract = "We study parametric inference for ergodic diffusion processes with a degenerate diffusion matrix. Existing research focuses on a particular class of hypo-elliptic Stochastic Differential Equations (SDEs), with components split into {\textquoteleft}rough{\textquoteright}/{\textquoteleft}smooth{\textquoteright} and noise from rough components propagating directly onto smooth ones, but some critical model classes arising in applications have yet to be explored. We aim to cover this gap, thus analyse the highly degenerate class of SDEs, where components split into further sub-groups. Such models include e.g. the notable case of generalised Langevin equations. We propose a tailored time-discretisation scheme and provide asymptotic results supporting our scheme in the context of high-frequency, full observations. The proposed discretisation scheme is applicable in much more general data regimes and is shown to overcome biases via simulation studies also in the practical case when only a smooth component is observed. Joint consideration of our study for highly degenerate SDEs and existing research provides a general {\textquoteleft}recipe{\textquoteright} for the development of time-discretisation schemes to be used within statistical methods for general classes of hypo-elliptic SDEs.",
author = "Y. Iguchi and A. Beskos and Matthew Graham",
year = "2024",
month = aug,
day = "31",
doi = "10.1016/j.spa.2024.104384",
language = "English",
volume = "174",
journal = "Stochastic Processes and their Applications",
issn = "0304-4149",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Parameter inference for degenerate diffusion processes

AU - Iguchi, Y.

AU - Beskos, A.

AU - Graham, Matthew

PY - 2024/8/31

Y1 - 2024/8/31

N2 - We study parametric inference for ergodic diffusion processes with a degenerate diffusion matrix. Existing research focuses on a particular class of hypo-elliptic Stochastic Differential Equations (SDEs), with components split into ‘rough’/‘smooth’ and noise from rough components propagating directly onto smooth ones, but some critical model classes arising in applications have yet to be explored. We aim to cover this gap, thus analyse the highly degenerate class of SDEs, where components split into further sub-groups. Such models include e.g. the notable case of generalised Langevin equations. We propose a tailored time-discretisation scheme and provide asymptotic results supporting our scheme in the context of high-frequency, full observations. The proposed discretisation scheme is applicable in much more general data regimes and is shown to overcome biases via simulation studies also in the practical case when only a smooth component is observed. Joint consideration of our study for highly degenerate SDEs and existing research provides a general ‘recipe’ for the development of time-discretisation schemes to be used within statistical methods for general classes of hypo-elliptic SDEs.

AB - We study parametric inference for ergodic diffusion processes with a degenerate diffusion matrix. Existing research focuses on a particular class of hypo-elliptic Stochastic Differential Equations (SDEs), with components split into ‘rough’/‘smooth’ and noise from rough components propagating directly onto smooth ones, but some critical model classes arising in applications have yet to be explored. We aim to cover this gap, thus analyse the highly degenerate class of SDEs, where components split into further sub-groups. Such models include e.g. the notable case of generalised Langevin equations. We propose a tailored time-discretisation scheme and provide asymptotic results supporting our scheme in the context of high-frequency, full observations. The proposed discretisation scheme is applicable in much more general data regimes and is shown to overcome biases via simulation studies also in the practical case when only a smooth component is observed. Joint consideration of our study for highly degenerate SDEs and existing research provides a general ‘recipe’ for the development of time-discretisation schemes to be used within statistical methods for general classes of hypo-elliptic SDEs.

U2 - 10.1016/j.spa.2024.104384

DO - 10.1016/j.spa.2024.104384

M3 - Journal article

VL - 174

JO - Stochastic Processes and their Applications

JF - Stochastic Processes and their Applications

SN - 0304-4149

M1 - 104384

ER -