Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/31896 
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKiesl, Hansen
dc.contributor.authorRässler, Susanneen
dc.date.accessioned2006-10-10-
dc.date.accessioned2010-05-14T11:22:40Z-
dc.date.available2010-05-14T11:22:40Z-
dc.date.issued2006-
dc.identifier.urihttp://hdl.handle.net/10419/31896-
dc.description.abstractData fusion techniques typically aim to achieve a complete data file from different sources which do not contain the same units. Traditionally, this is done on the basis of variables common to all files. It is well known that those approaches establish conditional independence of the specific variables given the common variables, although they may be conditionally dependent in reality. We discuss the objectives of data fusion in the light of their feasibility and distinguish four levels of validity that a fusion technique may achieve. For a rather general situation, we derive the feasible set of correlation matrices for the variables not jointly observed and suggest a new quality index for data fusion. Finally, we present a suitable and effcient multiple imputation procedure to make use of auxiliary information and to overcome the conditional independence assumption.en
dc.language.isoengen
dc.publisher|aInstitut für Arbeitsmarkt- und Berufsforschung (IAB) |cNürnbergen
dc.relation.ispartofseries|aIAB-Discussion Paper |x15/2006en
dc.subject.jelC11en
dc.subject.jelC15en
dc.subject.jelC81en
dc.subject.ddc330en
dc.subject.keywordDatenen
dc.subject.keywordDatenaufbereitungen
dc.subject.keywordDatenqualitäten
dc.subject.keywordKorrelationen
dc.subject.keywordValiditäten
dc.subject.keywordangewandte Statistiken
dc.subject.keywordmathematische Statistiken
dc.titleHow valid can data fusion be?-
dc.type|aWorking Paperen
dc.identifier.ppn518523101en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen
dc.identifier.repecRePEc:iab:iabdpa:200615en

Files in This Item:
File
Size
384.89 kB





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