Show simple item record

Files in this item


Item metadata

dc.contributor.authorFasiolo, Matteo
dc.contributor.authorPya, Natalya
dc.contributor.authorWood, Simon N.
dc.identifier.citationFasiolo , M , Pya , N & Wood , S N 2016 , ' A comparison of inferential methods for highly nonlinear state space models in ecology and epidemiology ' , Statistical Science , vol. 31 , no. 1 , pp. 96-118 .
dc.identifier.otherPURE: 244461907
dc.identifier.otherPURE UUID: cc7993bd-532e-404f-81bc-891b3038ffeb
dc.identifier.otherScopus: 84959449954
dc.descriptionMost of this work was undertaken at the University of Bath, where M.F. was a Ph.D. student, and it was supported in part by EPSRC Grants EP/I000917 and EP/K005251/1.en
dc.description.abstractHighly nonlinear, chaotic or near chaotic, dynamic models are important in fields such as ecology and epidemiology: for example, pest species and diseases often display highly nonlinear dynamics. However, such models are problematic from the point of view of statistical inference. The defining feature of chaotic and near chaotic systems is extreme sensitivity to small changes in system states and parameters, and this can interfere with inference. There are twomain classes ofmethods for circumventing these difficulties: information reduction approaches, such as Approximate Bayesian Computation or Synthetic Likelihood, and state space methods, such as Particle Markov chain Monte Carlo, Iterated Filtering or Parameter Cascading. The purpose of this article is to compare the methods in order to reach conclusions about how to approach inference with such models in practice. We show that neither class of methods is universally superior to the other. We show that state space methods can suffer multimodality problems in settings with low process noise or model misspecification, leading to bias toward stable dynamics and high process noise. Information reduction methods avoid this problem, but, under the correct model and with sufficient process noise, state space methods lead to substantially sharper inference than information reduction methods. More practically, there are also differences in the tuning requirements of different methods. Our overall conclusion is that model development and checking should probably be performed using an information reduction method with low tuning requirements, while for final inference it is likely to be better to switch to a state space method, checking results against the information reduction approach.
dc.relation.ispartofStatistical Scienceen
dc.rights© Institute of Mathematical Statistics, 2016. This work is made available online in accordance with the publisher’s policies. This is the final published version of the work, which was originally published at:
dc.subjectApproximate bayesian computationen
dc.subjectNonlinear dynamicsen
dc.subjectParticle filtersen
dc.subjectState space modelsen
dc.subjectStatistical ecologyen
dc.subjectQA Mathematicsen
dc.subjectStatistics and Probabilityen
dc.subjectStatistics, Probability and Uncertaintyen
dc.titleA comparison of inferential methods for highly nonlinear state space models in ecology and epidemiologyen
dc.typeJournal articleen
dc.description.versionPublisher PDFen
dc.contributor.institutionUniversity of St Andrews. School of Mathematics and Statisticsen
dc.description.statusPeer revieweden

This item appears in the following Collection(s)

Show simple item record