Bayesian model based spatiotemporal survey designs and partially observed log Gaussian Cox process

Show simple item record

dc.contributor.author Liu, Jia
dc.contributor.author Vanhatalo, Jarno
dc.date.accessioned 2020-02-24T11:49:02Z
dc.date.available 2020-02-24T11:49:02Z
dc.date.issued 2020-03
dc.identifier.citation Liu , J & Vanhatalo , J 2020 , ' Bayesian model based spatiotemporal survey designs and partially observed log Gaussian Cox process ' , Spatial statistics , vol. 35 , 100392 . https://doi.org/10.1016/j.spasta.2019.100392
dc.identifier.other PURE: 127335153
dc.identifier.other PURE UUID: b014cdd7-14ba-4d27-af37-bf9028cd7f54
dc.identifier.other WOS: 000516809600001
dc.identifier.uri http://hdl.handle.net/10138/312165
dc.description.abstract In geostatistics, the spatiotemporal design for data collection is central for accurate prediction and parameter inference. An important class of geostatistical models is log-Gaussian Cox process (LGCP) but there are no formal analyses on spatial or spatiotemporal survey designs for them. In this work, we study traditional balanced and uniform random designs in situations where analyst has prior information on intensity function of LGCP and show that the traditional balanced and random designs are not efficient in such situations. We also propose a new design sampling method, a rejection sampling design, which extends the traditional balanced and random designs by directing survey sites to locations that are a priori expected to provide most information. We compare our proposal to the traditional balanced and uniform random designs using the expected average predictive variance (APV) loss and the expected Kullback-Leibler (KL) divergence between the prior and the posterior for the LGCP intensity function in simulation experiments and in a real world case study. The APV informs about expected accuracy of a survey design in point-wise predictions and the KL-divergence measures the expected gain in information about the joint distribution of the intensity field. The case study concerns planning a survey design for analyzing larval areas of two commercially important fish stocks on Finnish coastal region. Our experiments show that the designs generated by the proposed rejection sampling method clearly outperform the traditional balanced and uniform random survey designs. Moreover, the method is easily applicable to other models in general. (C) 2019 The Author(s). Published by Elsevier B.V. en
dc.format.extent 27
dc.language.iso eng
dc.relation.ispartof Spatial statistics
dc.rights cc_by_nc_nd
dc.rights cc_by_nc_nd
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject 112 Statistics and probability
dc.subject Experimental design
dc.subject Bayesian inference
dc.subject Kullback-Leibler information
dc.subject Log Gaussian Cox process
dc.subject Rejection sampling design
dc.subject Species distribution
dc.subject POINT PROCESS MODELS
dc.subject PRESENCE-ONLY DATA
dc.subject INFERENCE
dc.subject INFORMATION
dc.subject SPACE
dc.title Bayesian model based spatiotemporal survey designs and partially observed log Gaussian Cox process en
dc.type Article
dc.contributor.organization Research Centre for Ecological Change
dc.contributor.organization Department of Mathematics and Statistics
dc.contributor.organization Organismal and Evolutionary Biology Research Programme
dc.contributor.organization Environmental and Ecological Statistics Group
dc.contributor.organization Biostatistics Helsinki
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1016/j.spasta.2019.100392
dc.relation.issn 2211-6753
dc.rights.accesslevel openAccess
dc.type.version publishedVersion
dc.type.version draft
dc.relation.funder SUOMEN AKATEMIA
dc.relation.funder SUOMEN AKATEMIA
dc.relation.grantnumber
dc.relation.grantnumber

Files in this item

Total number of downloads: Loading...

Files Size Format View
untitled.pdf 3.941Mb PDF View/Open
1_s2.0_S2211675319301435_main.pdf 1.624Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record