UNITED NATIONSECONOMIC COMMISSION FOR EUROPECONFERENCE OF EUROPEAN STATISTICIANSWork Session on Statistical Data Editing(Paris, France, 28-30 April 2014) HLG Modernization Committeeon Production and Methods Steven Vale (UNECE) Claude Poirier (Canada)
Introducing the HLG • High-level Group for the Modernisation of Statistical Production and Services • Created by the Conference of European Statisticians in 2010 • Vision and strategy endorsed by CES in 2011/2012
Who are the HLG members? • Pádraig Dalton (Ireland) - Chairman • Trevor Sutton (Australia) • Wayne Smith (Canada) • Emanuele Baldacci (Italy) • Bert Kroese (Netherlands) • Park, Hyungsoo (Republic of Korea) • GenovefaRužić (Slovenia) • Walter Radermacher (Eurostat) • Martine Durand (OECD) • Lidia Bratanova (UNECE)
What does the HLG do? • Oversees activities that support modernisation of statistical organisations • Stimulates development of global standards and international collaboration activities • “Within the official statistics community ... take a leadership and coordination role”
What has the HLG achieved? • 2012 • Generic Statistical Information Model • 2013 • Common Statistical Production Architecture • Frameworks and Standards for Statistical Modernisation • 2014 - Work in Progress • Implementation of the Common Statistical Production Architecture • Big Data in Official Statistics
HLG Modernization Committeeon Production and Methods • The membership • Chairs: MartonVucsan, Rune Gløersen • Participants: Australia, Canada, Hungary, Ireland, Italy, Moldova, Netherlands, New Zealand, Norway, Poland, Spain, Eurostat, OECD, UNIDO • The 2014 work plan • CSPA, BIG Data, Statistical Services, Survey on current tools, Development of official statistics, Machine learning, Strategic development (interconnected world)
Machine Learning • Opportunities for Methodologists and IT specialists to co-work • Get methodology vision with respect to modern services • Identify current methodology assets • Articulate methodology development around IT strengths • Influence IT initiative to enable state-of-the-art methods Production Less manual interventions Machine learning Get ready for BIG Data
Machine Learning (cont’d) • Machine learning: • Data editing • Automated coding • Record linkage • High potential to reduce if not eliminate manual work • Environmental scan to identifywherewe are at • Identification of local development plans • Roadmap to identifywhereweshould go Participants: Canada, Australia, Netherlands, Hungary, Poland, UNIDO Lead: Canada
Machine Learning (cont’d) • Deliverables • A report reviewing state-of-the-art machine learning methods and algorithms for editing, coding and linkage • A development roadmap taking advantage of local initiatives while avoiding duplication of works, and being IT-realistic Schedule • October 2014
What does this mean for the future of the SDE group? • The Statistical Data Editing group has been around for many years • Some successes, particularly sharing ideas and good practices • Could a different approach or a different format accelerate progress?
Some ideas • Silos – not just for subject matter people? • We should bring together: • Methodologists • IT experts • Information architects • Data scientists • .... • Multi-disciplinary approach to problem solving within organisations
So why keep silos for international meetings? • What sort of event would have the most value foryour organisation?