Institut für Arbeitsmarkt- und Berufsforschung

Navigation zu den wichtigsten Bereichen.


Zertifikat "audit berufundfamilie"

Inhaltsbereich: Institut für Arbeitsmarkt- und Berufsforschung

Nonresponse and Measurement Error in Employment Research





Projektleiterin / Projektleiter


September 2008


Dezember 2012


Survey methodologists are increasingly concerned with the interaction of multiple error sources. Particularly prominent are discussions about nonresponse and measurement error. One hypothesis that is often found among practitioners is that sample cases that are brought into the survey only after repeated attempts and alternated recruitment strategies, are more likely to provide low quality data. Data quality is often internally assessed through proportion of missing items, proportion of don t knows and the like. Rarely are external data available to evaluate the quality of respondents answers. The panel study PASS is a novel dataset in the field of labour market, welfare state and poverty research in Germany. In PASS survey data on the employment and unemployment history, income and education of participants can be linked to corresponding data from repondents adminstrative records. Furthermore the distributions of these variables in the sampling frame are known so that the total absolute bias can be assessed and decomposed into contributions due to nonresponse bias and measurement error bias. Based on this study we give an assessment of data quality as a function of contactability and response propensity. We are able to show that while internal indicators for data quality show no differences by contactability or response propensity measurement error is increased with decreasing contactability and response propensity of the target persons. This finding leads us to the question what the effect of repeated attempts and alternated recruitment startegies on total survey error is.


Based on PASS survey data, contact history data, and supplementary administrative data as a validation source, this paper jointly examines changes in nonresponse bias and measurement error bias of increasing levels of effort to recruit sample cases into the respondent pool.

Beteiligte Institute

  • Institut für Arbeitsmarkt- und Berufsforschung der Bundesagentur für Arbeit