Wednesday, March 27, 2013

Big Data and official statistics


Big Data is relevant to the production, relevance and reliability of key official statistics such as GDP and inflation.

Michael Horrigan, the head of the Bureau of Labor Statistics (BLS) Office of Prices and Living Conditions, provides a definition that helps clarify where the border lies between Big Data and traditional data. Big Data are non-sampled data that are characterized by the creation of databases from electronic sources whose primary purpose is something other than statistical inference.

Read more....

Wednesday, March 13, 2013

UNSD - Big Data for Policy, Development and Official Statistics

click to enlarge
Friday Seminar on Emerging Issues

Big Data for Policy,
Development and Official Statistics

22 February 2013, 10:00 am - 1:00 pm, 3:00 - 6:00 pm
Conference Rm. 2, Temporary North Lawn Building
United Nations, New York

The theme of this year’s Friday Seminar on Emerging Issues is: “Big Data for Policy, Development and Official Statistics”. The advent of the Internet, mobile devices and other technologies has caused a fundamental change to the nature of data. Big Data has important, distinct qualities that differentiate it from “traditional” institutional data, in particular the timeliness of the data. If governments wanted to, they could already let Big Data (and the private sector) play a role in providing information on topics that are currently under the purview of national statistical offices. Should these NSOs change their business operations to take on the opportunities of using Big Data for official government purposes?  
Please find below the provisional programme, the Key Questions and the Concept Note on Big Data for Policy, Development and Official Statistics. We encourage you to carefully read the key questions and to consider what they would imply for the work of your office. We are looking forward to your participation in this year’s Friday Seminar on Big Data. 
Organizer: United Nations Statistics Division (UNSD)
Morning Session, 10:00 - 13:00

 T.C. Anant, Chief Statistician, India
Hal Varian, Chief Economist, Google (Video)
 Matt Wood, Chief Data Scientist, Amazon Web Services 
 - James Goodnight, Chief Executive Officer, SAS
 Robert Kirkpatrick, Director, UN Global Pulse 
 Andrew Wyckoff, Director, Science, Technology and Industry, OECD 
Demonstrations Session, 14:00 - 15:00
 Howard Hamilton, Statistical Institute of Jamaica 
 Statistical Institute of Jamaica Video
 Matthias Helble, Universal Postal Union 
 - SAS
Afternoon Session, 15:00 - 18:00

 Brian Pink, Chief Statistician, Australia
Gosse Van der Veen, Chief Statistician, Netherlands Video
 William Bostic Jr., Associate Director, US Census Bureau 
 Ki-Jong Woo, Commissioner, Statistics Korea 
 Pali Lehohla, Chief Statistician, South Africa 
Background documents
1. Key questions
2. Concept note

Thursday, March 7, 2013

Placing Big Data in Official Statistics: A Big Challenge?



Monica Scannapieco1, Antonino Virgillito2, Diego Zardetto3
1Istat - Italian National Institute of Statistics, e-mail:
2Istat - Italian National Institute of Statistics, e-mail:
3Istat - Italian National Institute of Statistics, e-mail:


Big Data refers to data sets that are impossible to store and process using common
software tools, regardless of the computing power or the physical storage at hand. The
Big Data phenomenon is rapidly spreading in several domains including healthcare,
communication, social sciences and life sciences, just to cite some relevant examples.
However, the opportunities and challenges of Big Data in Official Statistics are matter of
an open debate that involves both statisticians and IT specialists of National Statistical
In this paper, we first analyse the concept of Big Data under the Official Statistics
perspective by identifying its potentialities and risks. Then, we provide some examples
that show how NSIs can deal with such a new paradigm by adopting Big Data
technologies, on one side, and rethinking methods to enable sound statistical analyses on
Big Data, on the other side.


Tuesday, March 5, 2013

Live webstreaming of NTTS 2013

If you're not able to attend NTTS 2013 in Brussels, you may still follow the conference online.

All sessions in the main auditorium (including the opening session, the closing session and all keynote speeches) will be transmitted via live webstreaming on the following addresses (separate address for each day):