Repository logo
 

Integrating geostatistical maps and infectious disease transmission models using adaptive multiple importance sampling

Published version
Peer-reviewed

Type

Article

Change log

Authors

Touloupou, P 
Basáñez, MG 
Déirdre Hollingsworth, T 
Spencer, SEF 

Abstract

The Adaptive Multiple Importance Sampling algorithm (AMIS) is an it-erative 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 geosta-tistical model of infectious disease prevalence, incidence or relative risk, and project it forward in time under a mathematical model for transmission dy-namics. We adapted the AMIS algorithm so that it can sample from multiple targets simultaneously by changing the focus of the adaptation at each itera-tion. By comparing our approach against the standard AMIS algorithm, we showed that these novel adaptations greatly improve the efficiency of the sam-pling. We tested the performance of our algorithm on four case studies: as-cariasis in Ethiopia, onchocerciasis in Togo, human immunodeficiency virus (HIV) in Botswana, and malaria in the Democratic Republic of the Congo.

Description

Keywords

Epidemiology, Disease mapping, Parameter estimation, Importance sampling

Journal Title

Annals of Applied Statistics

Conference Name

Journal ISSN

1932-6157
1941-7330

Volume Title

15

Publisher

Institute of Mathematical Statistics