Skip navigation
Skip navigation

Maximal autocorrelation factors for function-valued spatial/temporal data

Hooker, Giles; Roberts, Steven; Shang, Hanlin

Description

Dimension reduction techniques play a key role in analysing functional data that possess temporal or spatial dependence. Of these dimension reduction techniques functional principal components analysis (FPCA) remains a popular approach. Functional principal components extract a set of latent components by maximizing variance in a set of dependent functional data. However, this technique may fail to adequately capture temporal or spatial autocorrelation. Functional maximum autocorrelation...[Show more]

dc.contributor.authorHooker, Giles
dc.contributor.authorRoberts, Steven
dc.contributor.authorShang, Hanlin
dc.contributor.editorWeber, T.
dc.contributor.editorMcPhee, M.J.
dc.contributor.editorAnderssen, R.S.
dc.coverage.spatialGold Coast
dc.date.accessioned2016-06-14T23:21:28Z
dc.date.created29 Nov to 4 Dec 2015
dc.identifier.isbn9780987214355
dc.identifier.urihttp://hdl.handle.net/1885/103928
dc.description.abstractDimension reduction techniques play a key role in analysing functional data that possess temporal or spatial dependence. Of these dimension reduction techniques functional principal components analysis (FPCA) remains a popular approach. Functional principal components extract a set of latent components by maximizing variance in a set of dependent functional data. However, this technique may fail to adequately capture temporal or spatial autocorrelation. Functional maximum autocorrelation factors (FMAF) are proposed as an alternative for modeling and forecasting temporally or spatially dependent functional data. FMAF find linear combinations of the original functional data that have maximum autocorrelation and that are decreasingly predictable functions of time. We show that FMAF can be obtained by searching for the rotated components that have the smallest integrated first derivatives. Through a basis function expansion, a set of scores are obtained by multiplying the extracted FMAF with the original functional data. Autocorrelation in the original functional time series is manifested in the autocorrelation of these scores derived. Through a set of Monte Carlo simulation results, we study the finite-sample properties of the proposed FMAF. Wherever possible, we compare the performance between FMAF and FPCA. In an enhanced vegetation index data from Harvard Forest we apply FMAF to capture temporal or spatial dependency
dc.publisherThe Modelling and Simulation Society of Australia and New Zealand Inc.
dc.relation.ispartofseries21st International Congress on Modelling and Simulation (MODSIM2015)
dc.rightsAuthor/s retain copyright
dc.sourceMODSIM2015, 21st International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand
dc.source.urihttp://www.mssanz.org.au/modsim2015/index.html
dc.source.urihttp://www.mssanz.org.au/modsim2015/A3/hooker.pdf
dc.titleMaximal autocorrelation factors for function-valued spatial/temporal data
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2015
local.identifier.absfor010401 - Applied Statistics
local.identifier.ariespublicationu5260803xPUB63
local.type.statusPublished Version
local.contributor.affiliationHooker, Giles, Cornell University
local.contributor.affiliationRoberts, Steven, College of Business and Economics, ANU
local.contributor.affiliationShang, Hanlin, College of Business and Economics, ANU
local.bibliographicCitation.startpage159
local.bibliographicCitation.lastpage164
local.identifier.doi.36334/modsim.2015.a3.hooker
local.identifier.absseo829899 - Environmentally Sustainable Plant Production not elsewhere classified
local.identifier.absseo970101 - Expanding Knowledge in the Mathematical Sciences
dc.date.updated2021-08-01T08:39:58Z
dcterms.accessRightsOpen Access
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Hooker_Maximal_autocorrelation_2015.pdf4.91 MBAdobe PDF


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator