Contemporary statistical inference for infectious disease models using Stan

Anastasia Chatzilena; Edwin van Leeuwen; Oliver Ratmann; Marc Baguelin; Nikolaos Demiris

doi:10.1016/j.epidem.2019.100367

Contemporary statistical inference for infectious disease models using Stan

Anastasia Chatzilena^*, Edwin van Leeuwen, Oliver Ratmann, Marc Baguelin, Nikolaos Demiris

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

45 Citations (Scopus)

Abstract

This paper is concerned with the application of recent statistical advances to inference of infectious disease dynamics. We describe the fitting of a class of epidemic models using Hamiltonian Monte Carlo and variational inference as implemented in the freely available Stan software. We apply the two methods to real data from outbreaks as well as routinely collected observations. Our results suggest that both inference methods are computationally feasible in this context, and show a trade-off between statistical efficiency versus computational speed. The latter appears particularly relevant for real-time applications.

Original language	English
Article number	100367
Journal	Epidemics
Volume	29
DOIs	https://doi.org/10.1016/j.epidem.2019.100367
Publication status	Published - Dec 2019

Bibliographical note

Publisher Copyright:
© 2019 The Authors

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Automatic differentiation variational inference
Epidemic models
Hamiltonian Monte Carlo
No-U-turn sampler
Stan

Access to Document

10.1016/j.epidem.2019.100367

Handle.net

Persistent link

Cite this

@article{e9e12a43770343bebe56ac381c9278aa,

title = "Contemporary statistical inference for infectious disease models using Stan",

abstract = "This paper is concerned with the application of recent statistical advances to inference of infectious disease dynamics. We describe the fitting of a class of epidemic models using Hamiltonian Monte Carlo and variational inference as implemented in the freely available Stan software. We apply the two methods to real data from outbreaks as well as routinely collected observations. Our results suggest that both inference methods are computationally feasible in this context, and show a trade-off between statistical efficiency versus computational speed. The latter appears particularly relevant for real-time applications.",

keywords = "Automatic differentiation variational inference, Epidemic models, Hamiltonian Monte Carlo, No-U-turn sampler, Stan",

author = "Anastasia Chatzilena and \{van Leeuwen\}, Edwin and Oliver Ratmann and Marc Baguelin and Nikolaos Demiris",

note = "Publisher Copyright: {\textcopyright} 2019 The Authors",

year = "2019",

month = dec,

doi = "10.1016/j.epidem.2019.100367",

language = "English",

volume = "29",

journal = "Epidemics",

issn = "1755-4365",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Contemporary statistical inference for infectious disease models using Stan

AU - Chatzilena, Anastasia

AU - van Leeuwen, Edwin

AU - Ratmann, Oliver

AU - Baguelin, Marc

AU - Demiris, Nikolaos

PY - 2019/12

Y1 - 2019/12

N2 - This paper is concerned with the application of recent statistical advances to inference of infectious disease dynamics. We describe the fitting of a class of epidemic models using Hamiltonian Monte Carlo and variational inference as implemented in the freely available Stan software. We apply the two methods to real data from outbreaks as well as routinely collected observations. Our results suggest that both inference methods are computationally feasible in this context, and show a trade-off between statistical efficiency versus computational speed. The latter appears particularly relevant for real-time applications.

AB - This paper is concerned with the application of recent statistical advances to inference of infectious disease dynamics. We describe the fitting of a class of epidemic models using Hamiltonian Monte Carlo and variational inference as implemented in the freely available Stan software. We apply the two methods to real data from outbreaks as well as routinely collected observations. Our results suggest that both inference methods are computationally feasible in this context, and show a trade-off between statistical efficiency versus computational speed. The latter appears particularly relevant for real-time applications.

KW - Automatic differentiation variational inference

KW - Epidemic models

KW - Hamiltonian Monte Carlo

KW - No-U-turn sampler

KW - Stan

UR - https://www.scopus.com/pages/publications/85072795557

U2 - 10.1016/j.epidem.2019.100367

DO - 10.1016/j.epidem.2019.100367

M3 - Article (Academic Journal)

C2 - 31591003

AN - SCOPUS:85072795557

SN - 1755-4365

VL - 29

JO - Epidemics

JF - Epidemics

M1 - 100367

ER -

Contemporary statistical inference for infectious disease models using Stan

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this