Modernization of official statistics Eric Hermouet Statistics Division, ESCAP

advertisement

Modernization of official statistics

Eric Hermouet

Statistics Division, ESCAP hermouete.unescap@un.org

Changing environment

 The data deluge

 New competitors

 Changing user demand

 Economic pressure

2

The data deluge

The internet had 1800 exabytes of data in 2011 exa = 10^18

3

The data deluge

50 000 exabytes by

2020

Even if 99.9% are videos, photos, audio files, text messages etc., that still leaves a huge amount of potentially relevant data

4

New competitors

 Google:

– Real-time price indices

– Public Data Explorer

– First point of reference for the “data generation”

 Facebook, store cards, credit agencies, ...

– What if they link their data?

Can they provide an alternative to population censuses?

5

Changing user demands

 Statistics made available faster

 Need to answer wider range of user

– Need to package data differently

 Need for more detailed information

 Need for integrated data products

– Linking logically datasets from different sources

6

Response of official statistics community

 Develop and promote new:

Sources Processes Products

 High-Level Group for Strategic Directions in

Business Architecture in Statistics (HLG-BAS)

– Created by the Conference of European Statisticians in

2010

– 9 heads of national and international statistical organizations

7 Civil Registration and Vital Statistics

8

 The Challenges are too big for statistical organizations to tackle on their own.

We need to work together

 Collaboration

 Coordination

 Communication

9

What is modernization?

 Common processes

 Common tools

 Common methodologies

 Recognizing that all statistics are produced in a similar way:

No domain is “special”

 Increased flexibility to adapt to new sources and produce new outputs

10

Industry standards

G eneric

S tatistical

B usiness

P rocess

M odel

G eneric

S tatistical

I nformation

M odel

S tatistical D ata and M etadata e X change

D ata D ocumentation I nitiative

11

GSBPM – The Background

 Statistical production has traditionally been organised by topic, e.g. transport, trade, …

 Some statistical organisations are moving towards a process-based approach

12

GSBPM: Why do we need a model?

 To define and describe statistical processes in a coherent way

 To standardize process terminology

 To compare and benchmark processes within and between organisations

 To identify synergies between processes

 To inform decisions on systems architectures and organisation of resources

13

GSBPM: Applicability

 All activities undertaken by producers of official statistics which result in data outputs

 National and international statistical organisations

 Independent of data source, can be used for:

– Surveys / censuses

– Administrative sources / register-based statistics

– Mixed sources

14

15

Key features of GSBPM

Not a linear model

 Sub-processes do not have to be followed in a strict order

 It is a matrix, through which there are many possible paths, including iterative loops within and between phases

 Some iterations of a regular process may skip certain sub-processes

16

Other uses of the GSBPM

 Harmonizing statistical computing systems

 Facilitating sharing of statistical software

 Framework for process quality management

 Structure for storage of documents

 Measuring operational costs

18

GSIM

The Generic Statistical Information Model is a reference framework of information objects, which enables generic descriptions of data and metadata definition, management, and use throughout the statistical production process

 Another model is needed to describe data and metadata objects and flows within the statistical business process

19

GSIM

 Provide a common reference model for statistical information

 Define the information required to drive statistical production processes and define outputs

 Facilitate building efficient metadata driven collection, processing, and dissemination systems

20

Leads to a modular approach in designing software

Plug and play tools

21 Civil Registration and Vital Statistics

Related ESCAP activities

 EGM in June 2011

 SIAP Management Seminar in December 2011

 Moscow workshop, April 2012

 On the agenda of the upcoming Committee on

Statistics, December 2012

 http://www.unescap.org/stat/MSIS/index.asp

22 Civil Registration and Vital Statistics

Further information

 GSBPM

– http://www1.unece.org/stat/platform/display/metis/The+

Generic+Statistical+Business+Process+Model

 GSIM

– http://www1.unece.org/stat/platform/display/metis/Gene ric+Statistical+Information+Model+(GSIM)

 HLG-BAS

– http://www1.unece.org/stat/platform/display/hlgbas

23

24

THANK YOU.

Questions?

Civil Registration and Vital Statistics

Download