Tuesday 16th July
Wednesday 17th July
Thursday 18th July
Friday 19th July
Download the conference book
EU-SILC: Some key methodological outcomes of the Net-SILC2 EU project |
|
| Convenor | Mr Eric Marlier (International Scientific Coordinator of the CEPS/INSTEAD Research Centre) |
| Coordinator 1 | Mr Guillaume Osier (Luxembourg Income Study and STATEC) |
The "EU Statistics on Income and Living Conditions" (EU-SILC) covers the 27 EU countries and a number of other European countries. It is the main data source for comparative analysis and indicators on income and living conditions in the EU. Since the launch in June 2010 of the "Europe 2020" Strategy for smart, sustainable and inclusive growth, the importance of EU-SILC has grown further: one of the five Europe 2020 headline targets is based on EU-SILC data (the social inclusion EU target, which consists of lifting at least 20 million people in the EU from the risk of poverty and exclusion by 2020).
A lot of EU-SILC methodological work is being undertaken in the framework of the "Second Network for the Analysis of EU-SILC" (Net-SILC2). Funded by Eurostat for the period June 2011/ May 2015, Net-SILC2 brings together expertise from 16 European partners: the Luxembourg-based CEPS/INSTEAD Research Institute (Net-SILC2 coordinator), six National Statistical Institutes (from Austria, Finland, France, Luxembourg, Norway and the UK), the Bank of Italy and academics from 8 research bodies (in Belgium, Germany, Sweden and the UK). Two main aims of Net-SILC2 are: a) to carry out in-depth methodological work and socio-economic analysis based on EU-SILC data (covering both the cross-sectional and longitudinal dimensions of the instrument); and b) to develop common tools and approaches regarding various aspects of data production. Net-SILC2 is the successor of Net-SILC1 (Dec 2008/ Dec 2010) whose final output was a book on "Income and living conditions in Europe". This special "Net-SILC2 session" will consist of four methodological contributions prepared by some Net-SILC2 members.
EU-SILC is a survey on income and living conditions based on EU regulations which is carried out in all EU member states. EU-SILC is the source of many social indicators such as the at-risk-of-poverty rate. Another important indicator calculated with EU-SILC is the persistent at-risk-of-poverty rate, which relies on the longitudinal component of EU-SILC.
The EU regulation requires cross-sectional and longitudinal data. In most countries EU-SILC is implemented with an integrated design as a rotating panel. Hence, EU-SILC allows for a cross-sectional and for a longitudinal perspective. Although the samples of the cross-sectional and the longitudinal component overlap for large parts, in some countries significant discrepancies appear, if indicators based either on panel or cross-sectional data (i.e. variable or constant masses) are compared.
This presentation shows the scope of the discrepancies in certain EU member states and discusses possible reasons. In a hierarchical analysis of meta and micro data possible causes related to nonresponse as well as population change, sampling errors and the weighting process are investigated. In particular, we will assess the impact of attrition using indicators of representativity ("R-indicators").
Since EU-SILC was launched, much attention has been paid to data quality, mainly because the EU-SILC data are collected through sample surveys. However, the computation of standard errors for EU-SILC estimates is confronted with several challenges including, among others, complex sample designs, rotating samples, complex non-linear and longitudinal indicators and indicators of net changes. Besides, the publication schedule for EU-SILC includes a large number of statistics for which standard error estimates are quickly wanted. We present concrete recommendations that have been issued by Net-SILC2 with regard to standard error estimation, compromising between statistical accuracy and operational considerations (time, cost, simplicity…).
Access to administrative and statistical registers may influence the design and production of sample surveys in various ways. The presentation reviews the combined use of registers and interviews in EU-SILC, a cross-national output harmonised household survey designed to measure household income and living conditions in the European countries. The framework and design of EU-SILC explicitly take the combined use of registers into account. We discuss the EU-SILC designs in the "register countries" and the "survey countries", the pros and cons of joint use of register- and interview-based data, and assess the potential consequences for cross-national comparability in EU-SILC.
This paper assesses the EU-SILC following rules, covering both the regulatory framework and its implementation. We pay particular attention to household splits, focusing on the two most common associated transitions: partnership dissolution, and young adults leaving home. Using EU-SILC longitudinal data from 2003-2009, we find that in most countries, too few people are re-interviewed following partnership dissolutions for longitudinal analysis of these transitions to be feasible. For young adults leaving home, the percentages followed are higher: the determinants of home-leaving may be analysed in all countries, and the effects of home-leaving may be analysed in a subset of countries.
There has been increasing interest in recent years in analysing people’s exposure to poverty on multiple dimensions, including income, expenditure and material deprivation. However, no single data source provides joint information on all these variables. Therefore, this paper describes methodological work conducted to statistically (or synthetically) match expenditure from the Household Budget Survey (HBS) with income and material deprivation contained within EU Statistics on Income and Living Conditions (SILC). Three different approaches to statistical matching are used (parametric, non-parametric and mixed) and their effectiveness in matching expenditure is examined through a variety of measures.