A data–cleaning augmented Kalman filter for robust estimation of state space models

Simple item page
dc.contributor.authorMarczak, Martynade
dc.contributor.authorProietti, Tommasode
dc.contributor.authorGrassi, Stefanode
dc.date.accessioned2024-04-08T08:51:59Z
dc.date.available2024-04-08T08:51:59Z
dc.date.created2015-11-09
dc.date.issued2015
dc.description.abstractThis article presents a robust augmented Kalman filter that extends the data– cleaning filter (Masreliez and Martin, 1977) to the general state space model featuring nonstationary and regression effects. The robust filter shrinks the observations towards their one–step–ahead prediction based on the past, by bounding the effect of the information carried by a new observation according to an influence function. When maximum likelihood estimation is carried out on the replacement data, an M–type estimator is obtained. We investigate the performance of the robust AKF in two applications using as a modeling framework the basic structural time series model, a popular unobserved components model in the analysis of seasonal time series. First, a Monte Carlo experiment is conducted in order to evaluate the com- parative accuracy of the proposed method for estimating the variance parameters. Second, the method is applied in a forecasting context to a large set of European trade statistics series.en
dc.identifier.swb451518292
dc.identifier.urihttps://hohpublica.uni-hohenheim.de/handle/123456789/5965
dc.identifier.urnurn:nbn:de:bsz:100-opus-11563
dc.language.isoeng
dc.relation.ispartofseriesHohenheim discussion papers in business, economics and social sciences; 2015,13
dc.rights.licensepubl-mit-poden
dc.rights.licensepubl-mit-podde
dc.rights.urihttp://opus.uni-hohenheim.de/doku/lic_mit_pod.php
dc.subjectRobust filteringen
dc.subjectAugmented Kalman filteren
dc.subjectStructural time series modelen
dc.subjectAdditive outlieren
dc.subjectInnovation outlieren
dc.subject.ddc300
dc.subject.gndFilterung <Stochastik>de
dc.subject.gndHandelsstatistikde
dc.titleA data–cleaning augmented Kalman filter for robust estimation of state space modelsde
dc.type.dcmiTextde
dc.type.diniWorkingPaperde
local.accessuneingeschränkter Zugriffen
local.accessuneingeschränkter Zugriffde
local.bibliographicCitation.publisherPlaceUniversität Hohenheimde
local.export.bibtex@techreport{Marczak2015, url = {https://hohpublica.uni-hohenheim.de/handle/123456789/5965}, author = {Marczak, Martyna and Proietti, Tommaso and Grassi, Stefano et al.}, title = {A data–cleaning augmented Kalman filter for robust estimation of state space models}, year = {2015}, school = {Universität Hohenheim}, series = {Hohenheim discussion papers in business, economics and social sciences}, }
local.export.bibtexAuthorMarczak, Martyna and Proietti, Tommaso and Grassi, Stefano et al.
local.export.bibtexKeyMarczak2015
local.export.bibtexType@techreport
local.faculty.number3de
local.institute.number520de
local.opus.number1156
local.series.issueNumber2015,13
local.series.titleHohenheim discussion papers in business, economics and social sciences
local.universityUniversität Hohenheimde
local.university.facultyFaculty of Business, Economics and Social Sciencesen
local.university.facultyFakultät Wirtschafts- und Sozialwissenschaftende
local.university.instituteInstitute for Economicsen
local.university.instituteInstitut für Volkswirtschaftslehrede

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dp_13_2015_online.pdf
Size:
815.72 KB
Format:
Adobe Portable Document Format
Description:
Open Access Fulltext
Download

Collections

Institut für Volkswirtschaftslehre
Hohenheim discussion papers in business, economics and social sciences