Conferences

ESRA2009:

Conference main page

Overview of sessions

Time table

Warsaw 2009: Presentations and short courses

The EU Statistics on Income and Living: the Problem of Output Harmonization

Session: Non-response bias in cross-national surveys: an evaluation of Designs for detection and adjustment (II)

Authors:

Hans Schmeets; Statistics Netherlands (CBS), Netherlands
Bart Huynen; Statistics Netherlands (CBS), Netherlands

Abstract:

The mission of Eurostat – the statistical office of the EU – is “to provide the European Union with high-quality statistical information. For that purpose, it gathers and analyses figures from the national statistical offices across Europe and provides comparable and harmonised data for the European Union to use in the definition, implementation, and analysis of Community policies“.

Based on an EU regulation, the member states were requested to collect information on social and cultural participation in an additional module in the EU-survey Statistics on Income and Living (EU-SILC). According to the guidelines in the regulation, only the concepts (definitions) were defined. Consequently, the questionnaires varied substantially between the EU-states. In addition, several designs were used to conduct the information. In many ‘new’ member states a new survey was introduced, whereas in other countries existing samples, often based on registers, served as a base for collecting the data on social and cultural participation. At least three different interview modes were adopted: face-to-face, by telephone, and by mail. Other aspects varied widely, such as the response rates and the percentage of proxy-interviews.

The presentation deals with the comparison of the 2006 EU-SILC data on social and cultural participation in all EU-member states. It will be demonstrated that:

(a) The questions are differently phrased between the countries; in addition, the response rates and number of proxy-interviews differ substantially.

(b) The combination of ‘register’-countries and telephone interviews results in higher participation rates compared to the combination of ‘survey’-countries and face-to-face interviews;