PropertyValue
?:abstract
  • "In the past decades response rates have been declining for a large variety of surveys in a lot of countries all over the world (deLeeuw & deHeer 2001). Also the German General Social Survey (ALLBUS) has been facing an increase in nonresponse in the last years. The ALLBUS is a face-to-face survey of the adult population in Germany, which has been fielded every second year since 1980. Between 1996 and 2006, e.g., the response rate of ALLBUS has decreased from an already rather low level of 54 % in 1996 to 43 % in 2006. The basic question is whether this increase in nonresponse does also mean a reduction in data quality, in particular a higher nonresponse bias. Recent research has questioned, whether empirically a close relationship between the nonresponse rate and the size of the nonresponse bias can be observed (e.g. Groves 2006). In order to find out, whether an increase in response rates in ALLBUS would also mean different (and probably better, i.e. less biased) results, an experiment was implemented in 2008. The general idea was to compare the results of the regular ALLBUS 2008 (with an expected response rate of 45%) with the results of an additional sample (called ALLBUS +) in which intensive fieldwork efforts would (hopefully) result in a considerably higher response rate (targeted response rate of 70%). Amongst other things, the additional efforts to achieve a higher response rate included the deployment of a special group of interviewers, the personal briefing of interviewers, better payment of interviewers, and the use of respondent incentives. To decrease the respondent burden, also the interview length was reduced in the experimental sample from approximately 70 minutes to approximately 25 minutes on average. Both samples were fielded concurrently between March 2008 and July 2008.In our presentation we will describe the design and implementation of the study and present first results. We will provide an overview on the comparison of distributions between the regular ALLBUS and the ALLBUS+ sample, distinguishing between different types of variables. In addition, the stability or change of results over the fieldwork period will be analysed. In doing this, the emergence of differences in results between ALLBUS and ALLBUS + can be highlighted." (xsd:string)
?:author
?:comment
  • (ALLBUS) (xsd:string)
?:dataSource
  • ALLBUS-Bibliography (xsd:string)
?:dateCreated
  • Aufgenommen: 25. Fassung, März 2011 (xsd:gyear)
?:dateModified
  • 2008 (xsd:gyear)
?:datePublished
  • 2008 (xsd:gyear)
?:duplicate
is ?:hasPart of
?:inLanguage
  • english (xsd:string)
is ?:mainEntity of
?:name
  • Moving up. Does an increase in response mean different results? First evidence from an experimental study in the German General Social Survey 2008 (xsd:string)
?:publicationType
  • inproceedings (xsd:string)
?:reference
?:sourceCollection
  • ESRA Conference (xsd:string)
?:sourceInfo
  • Bibsonomy (xsd:string)
  • In ESRA Conference, 2008 (xsd:string)
?:startDate
  • 2009 (xsd:gyear)
?:studyGroup
  • ALLBUS (xsd:string)
?:tags
  • 2008 (xsd:string)
  • ALLBUS (xsd:string)
  • ALLBUS2008 (xsd:string)
  • ALLBUS_input2010 (xsd:string)
  • ALLBUS_pro (xsd:string)
  • ALLBUS_version25 (xsd:string)
  • FDZ_ALLBUS (xsd:string)
  • checked (xsd:string)
  • english (xsd:string)
  • inproceedings (xsd:string)
rdf:type