|Page tools: Print Page Print All|
This paper provides information on managing the quality of statistics produced from administrative data. It focusses on some principles and best practices to assist in the management of the acquisition of administrative data. It will be useful for any agency considering entering into a relationship regarding the supply and access of administrative data, as well as those agencies already involved in this area. A future publication is intended for release to cover processing issues which are not discussed in this paper.
This paper is a continuation of the ABS' role in providing guidance on frameworks and best practice in the use of statistics, including those produced from administrative data. It can be used in conjunction with other previously released ABS papers in the quality management series:
ABS Data Quality Framework, May 2009, (cat. no. 1520.0); and
Quality Management of Statistical Risk Using Quality Gates, Dec 2010, (cat. no. 1540.0).
Another useful source for quality management information is the National Statistical Services' Data Quality Online (http://www.nss.gov.au/dataquality/) tool which provides detailed information on the application of the ABS Data Quality Framework.
Administrative data consists of information collected about a population either directly or indirectly. It is collected by organisations for different administrative purposes including:
The administrative records can also be used for statistical purposes and in doing so can offer important advantages over direct collection of data from the population concerned.
Some examples of data sourced from administrative systems which have been used in ABS publications include:
In many ways the use of administrative data for the production of statistics or statistical analysis is akin to the production of statistics from data collected directly from respondents, as is done with a census or survey. Many of the principles and methods of best practice for the various processes involved apply regardless of the source, and the approaches for managing quality are the same. However, there are important differences which include (but are not limited to) the addition of at least one extra party in the acquisition of data and the fact that the administrative data are not collected for the sole purpose of statistical analysis. These differences and others need to be taken into consideration when using administrative data.
This paper will define the major uses of administrative data for statistical purposes and the quality management techniques which are important in the production of statistics. While this paper focuses primarily on acquiring electronic administrative data the principles can be applied to other forms of administrative data such as hospital record forms. Later releases will examine the processing of administrative data throughout the whole statistical cycle.
The term "data custodian" will be used to represent those agencies or organisations who collect administrative records as part of their normal business process requirements. "Receiving agency" will refer to those agencies or organisations who utilise administrative data for statistical purposes. Receiving agencies may include national statistical agencies or other government agencies or businesses who use administrative data to produce statistical outputs. In some cases it is possible that the data custodian and the receiving agency are the same entity.
These documents will be presented in a new window.