Syndicate content

What happens when big data meets official statistics?

Shaida Badiee's picture

Update: the event will be webstreamed on World Bank Live.

This is an exciting time to be in the data business. There have never been more groups, from such different backgrounds, with a passion for producing and using data for the public good.

What would happen if we brought some of these people together?


The official statistics community got its start in the 17th century, and has since been using surveys, censuses, registers and records to create statistics on all aspects of life for the public and government to use in making decisions and evaluating progress.


In the 21st century, official statistics is a mature discipline with National Statistics Offices and agencies like the UNSD and World Bank co-ordinating to build and implement the global standards, capacity and methodologies needed to produce good, dependable data.


When it comes to new ways of creating and presenting data - the mapping and geospatial data communities have made terrific progress with citizen mapping initiatives like this one the Bank has supported in Tandale; through mapping geo-coded aid information; and most recently in tying stories and media about development results to where work is happening on the ground.


And then there are the open data and big data communities who have emerged over the last 5 years. Through them, we’ve seen a huge increase in the use of public data, and more importantly, potential opportunities to use new data sources and techniques - that are often faster and cheaper - to supplement, or even replace some of the work of official statistics.


Can this really be done? Can we apply the same statistical rigour to big data sources and techniques to help meet the goals of official statistics?


Many of you joined us last month to hear how big data experts Jake Porway of DataKind, and Anthony Goldbloom of Kaggle are using data for the public good. I’d like to invite you to join us on December 19th to find out how official statistics experts Paul Cheung and Bob Groves are seeing the intersection of official statistics and big data, and the future of their discipline.


It’s going to be a great way to finish off a big year for all data - I look forward to seeing you there.


Please RSVP here as spaces are limited.


Submitted by K. Endriss on
Will there be livestreamed coverage, or a video online after the fact? Thanks!

You'll be able to join the session online at:

And also by following #bigstats on Twitter. We will post an archive of the video and I'll ask Paul if he wouldn't mind sharing his slides too.

Submitted by Michail Skaliotis on
This is a great event and we look forward to follow the discussion live! Developments are happening so fast in this field and are so pervassive that Official Statistical Agencies have a responsibility to address Big Data as an integral part of their annual and multi-annual work programmes.

Submitted by Paula on
Hello Shaida, This looks like a fantastic event. I would be very interested to hear what the future of Official Statistics looks like and would like to understand if there is a structure or gradient system in the works for Official Statistics? Since the event is sold out, is there a way to view the presentation afterwards? Thanks! Paula


You'll be able to join the session online at:

And also by following #bigstats on Twitter. We will post an archive of the video and I'll ask Paul if he wouldn't mind sharing his slides too.



Submitted by Piet Daas on
Great initative. We have been working on this topic at the official statistics office of the Netherlands for some time now. An overview of this work, with examples, can be found here

Submitted by Michail Skaliotis on
We look forward to listen to the discussion. Many thanks for livestreaming the event. In Eurostat we shall have 3 concrete projects starting early in 2013: (i)analysing internet traffic flows for producing ICT related official stats, (ii) use of mobile positioning data for tourism statistics and (iii) using the internet for collecting price statistics. Michail

Add new comment