Statistics: Investment in the Future Meeting of European Directors of Social Statistics Luxembourg, 24 and 25 September 2009 Walter Radermacher, Chief Statistician of the European Union, Director General Eurostat

Walter Radermacher, Eurostat 2 Statistics: a short history in 4 political steps „Statistics“ is the empirical branch of the science of state (German: Statistik –> Staatswissenschaften) Official statistics (political/administrative position, working methods) reflect the development of societies in particular the specific relationship between state and citizens Some factors create different political settings: –Constitution (democratic, authoritative) –Institutional set-up of economy (market, planification) –Society (closed/national, globalised) –Main sectors of economic production –Dynamics of structural change (slow, fast)

Walter Radermacher, Eurostat 3 Statistic users and producers: Interactions Users of statistics Producers of statistics information need use knowledge statistical information statistical data + metadata work system conducting of processes, provision of products and services discussion / definition perception patterns programmes products communication

Walter Radermacher, Eurostat 4 Information needs: Statistics Public Opinion Science Politics Institutional setup How are they defined?

Walter Radermacher, Eurostat 5 Statistics in a pre-democratic society State = authority = single constituent = single user Information needs defined by request of king or alternative authority First Statistical „Authorities“ as institutions Slow change processes (industrialisation) Development of work system with a small scientific loading Production in special processes; survey (obligatory response) based on authority of statistical institution Dissemination dominated by the user „State“, general publications as by-product

Walter Radermacher, Eurostat 6 Statistics in a “young” democracy / national state State = authority = premium constituent = premium user Information needs defined by request of government and/or parliament after consultation of stakeholders Statistical Institutes are “Cinderella” authorities Relatively slow change processes (industrialisation) Development of work system with a higher scientific loading Production in special processes; survey (obligatory response) based on authority of statistical institution Dissemination dominated by the user „State“, general publications as standard and equivalent product

Walter Radermacher, Eurostat 7 Statistics in an authoritarian regime State = authority = single constituent = single user Information needs defined by request of government Statistical Institute with high importance but low independency Focus on planification Development of work system with a very high scientific loading Production in special processes; survey (obligatory response) based on authority of statistical institution Dissemination oriented to the interests of the regime; impartiality not an issue

Walter Radermacher, Eurostat 8 Statistics in a democracy / global info society State is one user as all others (“citizens first”) Information needs defined in a dynamic and complex interaction (open platforms etc.) Statistical “Services” Rapid change processes, horizontal issues, cross- national phenomena Development of work system with a very high scientific loading Production in integrated processes; surveys limited to areas without existing data Dissemination = Communication = public good “Statistics”

Walter Radermacher, Eurostat The art of finding an adequate working system Actuality Comparability Response burden Accuracy Efficiency Relevance

Walter Radermacher, Eurostat 10 Convention and Measurement Statistical information - by definition - is produced based on conventions which manifest an agreement between user and producer regarding the parameters, methods and definitions of the working system In Official Statistics the convention has to be based on the information needs of the democratic society and it has to be made public (e.g. a UN Standard) In European Official Statistics the convention is fixed by a legal act / decision Professional independence in development, production and dissemination of official statistics is embedded in this framework of conventions

Walter Radermacher, Eurostat 11 European Coal and Steel Community (ECSC) in the early 1950s: The harmonisation of methods was the foundation of European statistics Rome Treaty on the European Economic Community (EEC) marked the birth of European legislation on statistics, for which the basis is laid in Art. 213 (subsequently Art. 284) => “Gentlemen's agreements“ Since the 1990s, European policies directly based on statistics (e.g. convergence criteria of the Maastricht Treaty ) The NSIs collect and produce harmonised data that are compiled by Eurostat to construct statistics at EU level. The approach continued to be "augmented": the European level was added to the national level European Statistics

Walter Radermacher, Eurostat 12 European Statistical System ESS Regulation (EC) No 223/2009 of the European Parliament and of the Council of 11 March 2009 on European Statistics Strengthens the cooperation in the ESS, in particular –cost-effectiveness-principle (Art. 2 (f)), –the European Statistical System Committee (Art. 7), –collaborative networks (Art. 15.), and a –European approach to statistics (Art. 16). Generally, a next phase for official statistics in Europe has been initiated, in which the intentions of the law, namely to put in place a real "system" that makes use of cooperation and standardisation as far as possible while respecting the subsidiarity principle have to be realised.

Walter Radermacher, Eurostat 13 Elements of the ESS ESS Committee (ESSC) European Statistical Advisory Committee (ESAC) European Statistical Governance Advisory Board (ESGAB) Partnership Group Directors Groups Comitology and advisory committees ESSnets Sponsorships DGINS and other conferences

Walter Radermacher, Eurostat 14 Organisational structure of the ESS ESSC

Walter Radermacher, Eurostat 15 Situation of Statistical Offices Need to reduce costs and increase efficiency Increasing demands for statistical products and reduction of respondent’s burden Improvements in quality are needed Emerging user needs Progress in information technology

Walter Radermacher, Eurostat 16 Starting points for a solution: Efficiency!! Standardisation of processes (CVD-approach) Re-use of available data (administrative sources, online link to business accounting and other instruments of eGovernment, …) Common infrastructure (registers, meta-data, geo-spatial information) Meta-data driven architecture Collaborative networks, common tools and knowledge sharing Decentralised centralisation of production in shared webs …

Walter Radermacher, Eurostat 17 Reengineering of statistical production 1:1 Stovepipes Multiple Source Mix Mode SurveyTable SurveyTable SurveyTable SurveyTable Survey Register Survey Data Ware- houses Macrodata Access Microdata Mesodata

Walter Radermacher, Eurostat 18 The new architecture: a vision GIS Business register Meta-data EntryProcessingAnalysis Primary surveys Administrative data repository ERP System Sample Selection External registers Communi cation Processes Infrastructure Input Output

Walter Radermacher, Eurostat 19 European systems method of statistics An integrated model for statistics in Europe: –horizontal integration across statistical domains at the level of NSIs and Eurostat, –and vertical integration covering both the national and EU levels. Improving efficiency by elimination of unnecessary variation and duplication of work Creation of free capacities for upcoming information needs

Walter Radermacher, Eurostat 20 Change in the professional paradigm From "data-collectors" to "re-users of data" Risks –concepts and definitions may be changed by the owners of the data –data collections could be discontinued or altered –a loss of control (at least in the perception of statisticians) –higher complexity Reallocation of R&D in statistics needed

Walter Radermacher, Eurostat 21 Technical and methodological challenges Standardisation and integration of formerly separated production processes will demand great efforts and an effective change management. Stepwise approach and with intensive collaboration Quality assessment + assurance of statistics will become much more complex The legitimate interest of statistics, i.e. the position vis-à- vis the owners of re-used data (administrators, regulators or others) has to be reconsidered and strengthened

Walter Radermacher, Eurostat 22 New ways of communicating with users The more statistical production is based on complex methodology the more it is necessary to explain the results. Trust in the statistical system and the perception of the quality of statistical information are closely related. „Official“ has to become a quality stamp that users can assess against predefined quality guidelines A basic education in simple statistical elements could help to mitigate a tendency of misunderstanding with the general public (“innumeracy”). As a consequence, user orientation has to be the guiding principle in communication.

Thank you for your attention!