Short-Term Economic Statistics (STES) Administrative Data: Two Frameworks of Papers

The STES Taskforce on Administrative Data: Two Frameworks of Papers is two ordered collections of administrative data papers describing good practice in the use of administrative data. The administrative data papers were provided by National Statistical Offices and these papers tend to focus on their experiences with administrative data in short-term economic statistics.

A working definition of administrative data

How to use the STES Taskforce on Administrative Data: Two Frameworks of Papers

The first framework ‘Broad administrative data categories’ provides direct access to documentation on good practice by National Statistical Institutes when using administrative data in compiling their statistics. As the title suggests, the papers are arranged by broad data categories based on purpose of use. As the use of administrative data throughout the world's statistical offices is varied and somewhat limited in the field of short-term economic statistics, the papers referenced within the categories have been further split to maximise the relevance of this framework to short-term economic statistics.

Framework – Broad administrative data categories

The second administrative data framework available below is structured to allow National Statistics Offices (NSOs) who are new to taking advantage of administrative data in the compilation of official statistics a path through the steps to incorporate administrative data into their compilation process.

Framework – Using administrative data

OECD welcomes feedback on these pages: please email stat.contact@oecd.org

Broad administrative data categories:
documentation on the use of administrative data in compiling and disseminating official statistics

1. Direct use of administrative data in registers
Most NSOs maintain a business register or business frame, and in an increasing number of these countries administrative data is being used extensively to maintain these registers.

2. Sampling frame/non-response control/imputation/non-response structure
In many cases administrative data can provide a full population dataset from which the survey sample can be drawn. This administrative data population can be further used to lessen the sample/survey error through non-response calculations and imputation.

3. Data or partial data substitution
For a number of NSOs, one of the core strengths of administrative data is the ability to use it directly in statistics through data substitution. In most cases this involves replacing a particular group of statistical unit, i.e. small businesses, in the survey population.

4. Data matching
This covers two types of matching:
1. Matching administrative data with survey data to improve the quality of both;
2. Matching two administrative datasets for either quality control or to create a longitudinal or panel dataset.

5. Quality, timeliness and coverage
The use of administrative data in short-term economic statistics has usually been associated with these three challenges (quality, timeliness and coverage) with the expected trade-off being the reduction in response burden, census coverage, and cost savings. This selection of papers covers these issues.

6. Quality control of administrative data
Some NSOs have the ability to influence the quality of the administrative data through direct contact with the providers. These papers are under this topic.

7. Handbooks or general papers
To date, at least two international organisations and one NSO have created different administrative data handbooks on specific administrative data topics. There have also been a number of papers by NSOs about how in general administrative data is used in their organisation. These papers are under this topic.

As a definition, Administrative Data can be said to have the following features:

the agent that supplies the data to the statistical agency and the unit to which the data relate are usually different: in contrast to most statistical surveys;
the data were originally collected for a definite non-statistical purpose that might affect the treatment of the source unit;
complete coverage of the target population is the aim;
control of the methods by which the administrative data are collected and processed rests with the administrative agency.

In most cases it is normal to accept (and expect) that the administrative agency will be a government unit that is responsible for implementing an administrative regulation.

Also AvailableEgalement disponible(s)