Digital Agenda, Big Data and Official Statistics

This article reviews three groups of questions: objectives placed before the Russian official statistics by the Digital Economy program; basic characteristics of the Big Data in terms of data  collection theory and design; concept of smart statistics. The article  addresses key issue of understanding Big Data as «organic data»  that are primary digital records kept in real time by software and  technology without human intervention. The use of Big Data in  official statistics leads to development of the new type of continuous statistical observation. First and foremost, digital nature  of Big Data and its basic characteristics, including as microdata,  provide new possibilities for measuring phenomenon and processes,  as well as determine the specific nature of observation errors that  occur when Big Data are generated. In general, the organization and process of generating Big Data are viewed by the author as the main type of statistical observation in the future. In the heart of the  concept of smart statistics lays direct incorporation of statistical  observation into the system of primary digital records followed by  the straight through automatic data processing up to compiling  statistical aggregates. The approaches discussed in this article are  linked to objectives placed before the Russian official statistics by the Digital Economy program.

1. Oksenoyt G.K. The target model - «Statistics-2025». Report at the Meeting of the Council on Open Data of the Government Commission for the Coordination of the Open Government, 23 December 2016. (In Russ.) Available from: http://www.gks.ru/free_doc/new_site/rosstat/smi/relizsod.pdf.

2. Suslov V.I. Economic Dimensions: Probability and Reliability, Mathematical Modeling, Big Data, E-statistics. Voprosy statistiki. 2016;(1):38-46. (In Russ.)

3. Karpova N.S., Surinov A.Ye., Uliyanov I.S. Problems and Possibilities for Using Big Data in the Russian Statistics. Voprosy statistiki. 2016;(7):3-9. (In Russ.)

4. Plekhanov D.A. Big Data and Official Statistics: a Review of International Experience with Integration of New Data Sources. Voprosy statistiki. 2017;(12):49- 60. (In Russ.)

5. World Bank, UNSD. Big Data Project Inventory. Available from: https://unstats.un.org/bigdata/inventory.

6. Hammer C.L., Kostroch D.C., Quirós G., STA Internal Group. Big Data: Potential, Challenges, and Statistical Implications. IMF Staff Discussion Note no. 17/06. September 2017.

7. A Suggested Framework for the Quality of Big Data. Deliverables of the UNECE Big Data Quality Task Team. December 2014. Available from: http://www1.unece.org/stat/platform/display/bigdata.

8. Vale S., UNECE Task Team on Big Data. Classification of Types of Big Data. 27 June 2013. Available from: https://statswiki.unece.org/display/bigdata/Classification+of+Types+of+Big+Data.

9. Eurostat Big Data Task Force. Item 8 of the agenda. ESS Big Data Action Plan and Roadmap 1.0. Work Programme Objective 11.1. ESSC 2014/22/8/EN - 26/09/2014.

10. 22nd Meeting of the European Statistical System Committee, 26 September 2014, Riga (Latvia).

11. Morgenshtern O. On the accuracy of economic observations. Moscow: Statistika Publ.; 1968. 293 p. (In Russ.)

12. Groves R.M. A Possible Data Future for the Observational Social Sciences. 2 November 2011. Available from: http://studylib.net/doc/11556583/a-possible-data- futurefor-the-observational-social-sciences.

13. Groves R.M. Data Production in Organic Data. The Provost’s Blog. Weblog. 19 August 2015. Available from: https://blog.provost.georgetown.edu/data-production- inorganic-data.

14. Barbosa A. Innovation and Modernization of National Statistical Systems Through «Trusted Data Collaboratives ». Keynote Speech. Proc. of the 4th International UN Conference on Big Data for Official Statistics, 8 November 2017, Bogota, Colombia.

15. Buono D. Eurostat Big Data Task Force. Item 4. Smart Statistics. 9 February 2017. Available from: https://ec.europa.eu/eurostat/cros/content/item-4-smart-statistics_en.