Course for Doctoral Students RESEARCH DATA MANAGEMENT AND OPEN DATA 25th July 2015, Social Science Data Arhives, Faculty of Social Sciences, University of Ljubljana ECPR Summer School 2015 ACCESS TO SOCIAL SCIENCE DATA: RESEARCH, ELECTION RESULTS, OFFICIAL STATISTICS Irena Vipavc Brvar, Sebastian Kočar, Janez Štebe Social Science Data Archives Content • Popular portals for Social Scientists • CESSDA • European Social Survey • European Election Database • Atlas of European Values • Official Statistics microdata • DWB project and training courses • metadata systems CIMES and MISSY • Access to EU official statistics microdata and aggregate data • Access to census microdata • Access to official statistics microdata in Slovenia /SI-STAT data portal International data ZACAT, DBK, DATORIUM Basic registration required CESSDA Members Austria Czech Republic Denmark Finland France Germany Greece Lithuania Netherlands Norway Slovenia Sweden Switzerland United Kingdom 29 Countries Let’s start with a simple exercise comparing life satisfaction measures of two groups – the unemployed people looking for work versus people in paid work. Calculate the means for the two groups across Europe. Source: European Social Survey, 2014 Politics Socio-demographics Source: European Social Survey, 2014 Source: European Social Survey, 2014 B20. All things considered, how satisfied are you with your life as a whole nowadays? Source: European Social Survey, 2014 Source: European Social Survey, 2014 Satisfaction with life vs. employment Next, let’s confirm the correlation between providing help and life satisfaction. Is it significant? Make sure you check variables response codes to be sure – for ex. do high numbers mean satisfaction or do they mean low satisfaction? Use the variables ‘(B20) How satisfied with life as a whole’ and ‘(D37) Provide help and support to people you are close to’. Source: European Social Survey, 2014 Politics Personal and social well-being Source: European Social Survey, 2014 Source: European Social Survey, 2014 Use help!! SPSS, STATA, SAS, R FINDING DATA ADVANCED SEARCH Atlas of European Values About DwB project • European Commission supported 4-year project 2011- 2015 • Supporting equal and easy access to official statistics (OS) microdata for the European research area • Bridging three communities (national statistics institutes, (social science) data archives/services, scientific researchers and research institutes) • Servicing researchers with official statistics metadata • Developing standards, microdata access procedures, regulation and legislation, also for transnational access • Promoting using OS microdata for research purposes (organizing workshops, staff visits, conferences) Training for microdata users • DwB organized 6 training courses for microdata users in 6 different countries • Target group: microdata users such as scientific researchers or PhD students • Structure of training courses: Theoretical part, about microdata access to European OS microdata Hands on sessions, working with carefully prepared, integrated and harmonized Eurostat microdata Focus on either Adult Education Survey, EU Labour Force Survey, EU Statistics on Income and Living Conditions or Integrated European Census Microdata • Similar training organized by GESIS in Mannheim, Germany CIMES - Centralising and Integrating Metadata from European Statistics • information system providing an overview of European official microdata disseminated for research purposes • structured metadata for national official statistics microdata • 3 levels of metadata: series, study and dataset • 31 European countries, 248 series, 1570 studies, 1821 datasets documented MISSY - Microdata Information System for Official Statistics • online service platform providing structured metadata for official statistics, including Eurostat microdata • covering Adult Education Survey, EU Labour Force Survey, EU Statistics on Income and Living Conditions, Community Innovation Survey, Structure of Earnings Survey • 5 levels of metadata: series, study, country study, dataset and variable levels • distribution channel for „setup files“ – software program codes codes for import and basic processing of EU microdata Access to European official statistics microdata • Eurostat harmonizes and merges microdata for official statistics research of national statistical offices • Eurostat also distributes the microdata for scientific use • microdata are available for researchers of organizations, which are recognized as a research entity • LFS, CIS, SES, EU-SILC, AES, CVTS (Continuing Vocational Training Survey), CSIS (Community Statistics on information Society), ERFT (European Road Freight Transport Survey), MMD (Micro-Moments Dataset) datasets • two modes of access to microdata: on electronic devices (CD/DVD) – anonymized versions in the safe centre in Luxembourg – non-anonymized versions Access to Eurostat official statistics aggregated data • publically available data in the form of tables • users can create their own tables by managing the display (countries, statistics, variables etc.) Access to census microdata • Access to detailed microdata (ScUF): Statistical Office of the Republic of Slovenia distributes Slovenian Census microdata (2002, 2011, 2015 coming soon) • Access to moderately protected microdata (SUF): IECM/IPUMS Europe distributes European census data (19 countries, 55 censuses and totaling more than 90 million person records) – emphasis on harmonization • Access to anonymized microdata (PUF): Slovenian Social Science Data Archives distribute Slovenian Census microdata (2002, 2011) – limited number of variables, less detailed data (aggregated variable values) Access to official statistics microdata in Slovenia • access to microdata for research and analysis enabled by the Statistical Office of the Republic of Slovenia • available to Slovenian and international researchers (researchers in the general government sector, registered research institutions, registered researchers, also students working with registered researchers) • three modes of access: safe room, remote access, DVDs • theoretically, all microdata listed in the Annual Programmes of Statistical Surveys could be available • requests are handled by the Data Protection Committee; a contract should be signed if access approved SI-STAT data portal • data in the form of tables, provided by the Statistical Office of the Republic of Slovenia • one-stop access to statistical data from different fields of statistics and different sources Collaboration of the Slovenian Social Science Data Archives and the Statistical Office • both organizations were partners of the DwB project • collaboration in the national level, consolidating partners‘ expert knowledge and experience • preparing metadata for the most important official statistics microdata • preparing microdata (e.g. LFS, register data, Census microdata) for immediate statistical analyses with the selected statistical software package promoting microdata use for research purposes • organizing workshops for students to promote microdata use for study purposes (distributing Public Use Files) Overview • recognizing research potential in official statistics data • increasing support for microdata access in the European area (also for transnational access and remote access) • establishing national collaborations to improve microdata access services • various publically available aggregated data sources • improving metadata systems and availability of metadata to support release of microdata • increasing need for distribution of Public Use Files - publically available protected microdata Questions?