Full metadata record
DC FieldValueLanguage
dc.contributor.authorMorik, Katharina-
dc.contributor.authorPumplün, Constanze-
dc.contributor.authorRüping, Stefan-
dc.contributor.authorWeihs, Claus-
dc.date.accessioned2005-11-07T11:40:01Z-
dc.date.available2005-11-07T11:40:01Z-
dc.date.issued2005-11-07T11:40:01Z-
dc.identifier.urihttp://hdl.handle.net/2003/21668-
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-14490-
dc.description.abstractThis paper investigates the use of Design of Experiments in observational studies in order to select informative observations and features for classification. D-optimal plans are searched for in existing data and based on these plans the variables most relevant for classification are determined. The adapted models are then compared with respect to their predictive accuracy on an independent test sample. Eight different data sets are investigated by this method.en
dc.format.extent161501 bytes-
dc.format.mimetypeapplication/pdf-
dc.language.isoen-
dc.subjectD-optimalityen
dc.subjectFeature Selectionen
dc.subjectGenetic Algorithmen
dc.subjectPrototypesen
dc.subject.ddc004-
dc.titleD-optimal plans in observational studiesen
dc.typeText-
dc.type.publicationtypereporten
dcterms.accessRightsopen access-
Appears in Collections:Sonderforschungsbereich (SFB) 475

Files in This Item:
File Description SizeFormat 
tr44-05.pdfDNB157.72 kBAdobe PDFView/Open


This item is protected by original copyright



This item is protected by original copyright rightsstatements.org