Integrating geostatistical maps and infectious disease transmission models using Adaptive Multiple Importance Sampling
File(s)
Published version
Author(s)
Retkute, Renata
Touloupou, Panayiota
Basanez, Maria-Gloria
Hollingsworth, T Deirdre
Spencer, Simon EF
Type
Journal Article
Abstract
The Adaptive Multiple Importance Sampling algorithm (AMIS)
is an iterative technique which recycles samples from all previous
iterations in order to improve the efficiency of the proposal distribution. We have formulated a new statistical framework, based on
AMIS, to take the output from a geostatistical model of infectious
disease prevalence, incidence or relative risk, and project it forward
in time under a mathematical model for transmission dynamics. We
adapted the AMIS algorithm so that it can sample from multiple targets simultaneously by changing the focus of the adaptation at each
iteration. By comparing our approach against the standard AMIS algorithm, we showed that these novel adaptations greatly improve the
efficiency of the sampling. We tested the performance of our algorithm
on four case studies: ascariasis in Ethiopia, onchocerciasis in Togo,
human immunodeficiency virus (HIV) in Botswana, and malaria in
the Democratic Republic of the Congo.
is an iterative technique which recycles samples from all previous
iterations in order to improve the efficiency of the proposal distribution. We have formulated a new statistical framework, based on
AMIS, to take the output from a geostatistical model of infectious
disease prevalence, incidence or relative risk, and project it forward
in time under a mathematical model for transmission dynamics. We
adapted the AMIS algorithm so that it can sample from multiple targets simultaneously by changing the focus of the adaptation at each
iteration. By comparing our approach against the standard AMIS algorithm, we showed that these novel adaptations greatly improve the
efficiency of the sampling. We tested the performance of our algorithm
on four case studies: ascariasis in Ethiopia, onchocerciasis in Togo,
human immunodeficiency virus (HIV) in Botswana, and malaria in
the Democratic Republic of the Congo.
Date Issued
2021-12
Date Acceptance
2021-05-17
Citation
Annals of Applied Statistics, 2021, 15 (4), pp.1980-1998
ISSN
1932-6157
Publisher
Institute of Mathematical Statistics
Start Page
1980
End Page
1998
Journal / Book Title
Annals of Applied Statistics
Volume
15
Issue
4
Copyright Statement
© 2021 The Author(s). This work is licensed under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/
License URL
Sponsor
The Task Force for Global Health
Bill & Melinda Gates Foundation
Medical Research Council (MRC)
Bill & Melinda Gates Foundation
The Task Force for Global Health
Identifier
https://projecteuclid.org/journals/annals-of-applied-statistics/volume-15/issue-4/Integrating-geostatistical-maps-and-infectious-disease-transmission-models-using-adaptive/10.1214/21-AOAS1486.full
Grant Number
MA4501180169
WPIA_P65811
MR/R015600/1
CRR00140
1708CR001/VP1 (OPP1184344)
Subjects
Science & Technology
Physical Sciences
Statistics & Probability
Mathematics
Epidemiology
Disease mapping
Parameter estimation
Importance sampling
AFRICA
ONCHOCERCIASIS
ELIMINATION
PREVALENCE
FREQUENCY
INFERENCE
Statistics & Probability
0104 Statistics
1403 Econometrics
Publication Status
Published
Date Publish Online
2021-12