PropertyValue
?:abstract
  • A new method to handle heterogeneity in paired comparison data is proposed. The preference of an item over another item is modelled depending on covariates of the subjects. The model allows for heterogeneity between subjects as the preference for an item can vary between subjects depending on subject-specific covariates. The model is estimated with a regularized estimation approach penalizing the differences between the subject-specific parameters corresponding to covariates. The specific penalty term allows for variable selection and for clusters of items regarding certain covariates. The method is applied to data from a pre-election study from Germany. (xsd:string)
?:author
?:comment
  • (GLES) (xsd:string)
?:dataSource
  • GLES-Bibliography (xsd:string)
?:dateCreated
  • 6. Fassung, Januar 2017 (xsd:gyear)
?:dateModified
  • 2015 (xsd:gyear)
?:datePublished
  • 2015 (xsd:gyear)
?:duplicate
is ?:hasPart of
is ?:mainEntity of
?:name
  • BTL-Lasso – A Penalty Approach to Heterogeneity in Paired Comparison Data (xsd:string)
?:publicationType
  • inproceedings (xsd:string)
?:reference
?:sourceCollection
  • 30. International Workshop on Statistical Modelling (xsd:string)
?:sourceInfo
  • Bibsonomy (xsd:string)
  • In 30. International Workshop on Statistical Modelling, 2015 (xsd:string)
?:startDate
  • 06.07-10.07.2015 (xsd:gyear)
?:studyGroup
  • German Longitudinal Election Study (GLES) (xsd:string)
?:tags
  • 2015 (xsd:string)
  • FDZ_Wahlen (xsd:string)
  • GLES (xsd:string)
  • GLES_input2016 (xsd:string)
  • GLES_pro (xsd:string)
  • GLES_version6 (xsd:string)
  • ZA5700 (xsd:string)
  • checked (xsd:string)
  • inproceedings (xsd:string)
rdf:type