A variance shilf model for outlier detection and estimation in linear and linear mixed models

Simple item page
dc.contributor.authorGumedze, Freedom Nkhululekoen_ZA
dc.date.accessioned2014-07-30T17:44:02Z
dc.date.available2014-07-30T17:44:02Z
dc.date.issued2008en_ZA
dc.descriptionIncludes abstract.
dc.descriptionIncludes bibliographical references.
dc.description.abstractOutliers are data observations that fall outside the usual conditional ranges of the response data.They are common in experimental research data, for example, due to transcription errors or faulty experimental equipment. Often outliers are quickly identified and addressed, that is, corrected, removed from the data, or retained for subsequent analysis. However, in many cases they are completely anomalous and it is unclear how to treat them. Case deletion techniques are established methods in detecting outliers in linear fixed effects analysis. The extension of these methods to detecting outliers in linear mixed models has not been entirely successful, in the literature. This thesis focuses on a variance shift outlier model as an approach to detecting and assessing outliers in both linear fixed effects and linear mixed effects analysis. A variance shift outlier model assumes a variance shift parameter, wi, for the ith observation, where wi is unknown and estimated from the data. Estimated values of wi indicate observations with possibly inflated variances relative to the remainder of the observations in the data set and hence outliers. When outliers lurk within anomalous elements in the data set, a variance shift outlier model offers an opportunity to include anomalies in the analysis, but down-weighted using the variance shift estimate wi. This down-weighting might be considered preferable to omitting data points (as in case-deletion methods). For very large values of wi a variance shift outlier model is approximately equivalent to the case deletion approach.en_ZA
dc.identifier.apacitationGumedze, F. N. (2008). <i>A variance shilf model for outlier detection and estimation in linear and linear mixed models</i>. (Thesis). University of Cape Town ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/4381en_ZA
dc.identifier.chicagocitationGumedze, Freedom Nkhululeko. <i>"A variance shilf model for outlier detection and estimation in linear and linear mixed models."</i> Thesis., University of Cape Town ,Faculty of Science ,Department of Statistical Sciences, 2008. http://hdl.handle.net/11427/4381en_ZA
dc.identifier.citationGumedze, F. 2008. A variance shilf model for outlier detection and estimation in linear and linear mixed models. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Gumedze, Freedom Nkhululeko AB - Outliers are data observations that fall outside the usual conditional ranges of the response data.They are common in experimental research data, for example, due to transcription errors or faulty experimental equipment. Often outliers are quickly identified and addressed, that is, corrected, removed from the data, or retained for subsequent analysis. However, in many cases they are completely anomalous and it is unclear how to treat them. Case deletion techniques are established methods in detecting outliers in linear fixed effects analysis. The extension of these methods to detecting outliers in linear mixed models has not been entirely successful, in the literature. This thesis focuses on a variance shift outlier model as an approach to detecting and assessing outliers in both linear fixed effects and linear mixed effects analysis. A variance shift outlier model assumes a variance shift parameter, wi, for the ith observation, where wi is unknown and estimated from the data. Estimated values of wi indicate observations with possibly inflated variances relative to the remainder of the observations in the data set and hence outliers. When outliers lurk within anomalous elements in the data set, a variance shift outlier model offers an opportunity to include anomalies in the analysis, but down-weighted using the variance shift estimate wi. This down-weighting might be considered preferable to omitting data points (as in case-deletion methods). For very large values of wi a variance shift outlier model is approximately equivalent to the case deletion approach. DA - 2008 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2008 T1 - A variance shilf model for outlier detection and estimation in linear and linear mixed models TI - A variance shilf model for outlier detection and estimation in linear and linear mixed models UR - http://hdl.handle.net/11427/4381 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/4381
dc.identifier.vancouvercitationGumedze FN. A variance shilf model for outlier detection and estimation in linear and linear mixed models. [Thesis]. University of Cape Town ,Faculty of Science ,Department of Statistical Sciences, 2008 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/4381en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentDepartment of Statistical Sciencesen_ZA
dc.publisher.facultyFaculty of Scienceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherStatistical Sciencesen_ZA
dc.titleA variance shilf model for outlier detection and estimation in linear and linear mixed modelsen_ZA
dc.typeDoctoral Thesis
dc.type.qualificationlevelDoctoral
dc.type.qualificationnameStatistical Sciencesen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_sci_2008_gumedze_f_g.pdf
Size:
1.81 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Other Theses