Assessing Nonresponse Bias with Microdata from Official Statistics the European Case

Thursday, July 17, 2014: 4:30 PM
Room: 416
Oral Presentation
Christof WOLF , Monitoring Society and Social Change, Leibniz Institute for Social Sciences, Mannheim, Germany
“Data without Boundaries” – a project funded under the 7th European Framework Programme – aims at improving access to microdata from official statistics in Europe. This overarching goal is reached through several tasks, among them: compiling information on available data and access conditions, proposals for harmonized accreditation access conditions, building a remote access network and offering web-based, structured and searchable codebooks for Eurostat data. Among the data sources that Eurostat produces and disseminates and that “Data without Boundaries” is creating a service for is the European Union Labour Force Survey, the largest household survey of the continent. EU-LFS is a continuous household survey currently carried out in 33 countries. In many of these countries EU-LFS is mandatory leading to very high response rates. Because of its size and the high quality of its sampling this survey is often used as benchmark to measure nonresponse bias in social surveys.

After introducing “Data without Boundaries” the presentation will demonstrate how EU-LFS can be exploited to assess nonresponse bias in surveys conducted in Europe. The empirical analysis focusses on the European Social Survey, the European Values Study and the European part of the International Social Survey Programme. Nonresponse bias will be assessed relative to the variables sex, age, education, employment status, household size and where available region or size of place.

The analysis demonstrates how not only those directly interested in micro data from official statistics but also survey researches benefit from the efforts of “Data without Boundaries” and the improved access to Eurostat’s data.