Gaussian process approximations for fast inference from infectious disease data

Elizabeth Buckingham-Jeffery; Valerie Isham; Thomas House

doi:10.1016/j.mbs.2018.02.003

Gaussian process approximations for fast inference from infectious disease data

Elizabeth Buckingham-Jeffery, Valerie Isham, Thomas House

Research output: Contribution to journal › Article › peer-review

Abstract

We present a flexible framework for deriving and quantifying the accuracy of Gaussian process approximations to non-linear stochastic individual-based models of epidemics. We develop this for the SIR and SEIR models, and show how it can be used to perform quick maximum likelihood inference for the underlying parameters given population estimates of the number of infecteds or cases at given time points. We also show how the unobserved processes can be inferred at the same
time as the underlying parameters.

Original language	English
Pages (from-to)	111-120
Journal	Mathematical Biosciences
Volume	301
Early online date	20 Feb 2018
DOIs	https://doi.org/10.1016/j.mbs.2018.02.003
Publication status	Published - Jul 2018

Keywords

SIR
SEIR
Stochastic Taylor Expansion
MLE

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.mbs.2018.02.003Licence: CC BY

Cite this

@article{9f8781142f6f4ca99de90459ae2881d7,

title = "Gaussian process approximations for fast inference from infectious disease data",

abstract = "We present a flexible framework for deriving and quantifying the accuracy of Gaussian process approximations to non-linear stochastic individual-based models of epidemics. We develop this for the SIR and SEIR models, and show how it can be used to perform quick maximum likelihood inference for the underlying parameters given population estimates of the number of infecteds or cases at given time points. We also show how the unobserved processes can be inferred at the sametime as the underlying parameters.",

keywords = "SIR, SEIR, Stochastic Taylor Expansion, MLE",

author = "Elizabeth Buckingham-Jeffery and Valerie Isham and Thomas House",

year = "2018",

month = jul,

doi = "10.1016/j.mbs.2018.02.003",

language = "English",

volume = "301",

pages = "111--120",

journal = "Mathematical Biosciences",

issn = "0025-5564",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Gaussian process approximations for fast inference from infectious disease data

AU - Buckingham-Jeffery, Elizabeth

AU - Isham, Valerie

AU - House, Thomas

PY - 2018/7

Y1 - 2018/7

N2 - We present a flexible framework for deriving and quantifying the accuracy of Gaussian process approximations to non-linear stochastic individual-based models of epidemics. We develop this for the SIR and SEIR models, and show how it can be used to perform quick maximum likelihood inference for the underlying parameters given population estimates of the number of infecteds or cases at given time points. We also show how the unobserved processes can be inferred at the sametime as the underlying parameters.

AB - We present a flexible framework for deriving and quantifying the accuracy of Gaussian process approximations to non-linear stochastic individual-based models of epidemics. We develop this for the SIR and SEIR models, and show how it can be used to perform quick maximum likelihood inference for the underlying parameters given population estimates of the number of infecteds or cases at given time points. We also show how the unobserved processes can be inferred at the sametime as the underlying parameters.

KW - SIR

KW - SEIR

KW - Stochastic Taylor Expansion

KW - MLE

U2 - 10.1016/j.mbs.2018.02.003

DO - 10.1016/j.mbs.2018.02.003

M3 - Article

SN - 0025-5564

VL - 301

SP - 111

EP - 120

JO - Mathematical Biosciences

JF - Mathematical Biosciences

ER -

Gaussian process approximations for fast inference from infectious disease data

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this