1522.0 - Quality Management of Statistical Outputs Produced From Administrative Data, Mar 2011  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 22/03/2011   
   Page tools: Print Print Page Print all pages in this productPrint All  


There is usually limited opportunity to influence the data by influencing the business processes underlying the creation of the administrative data. This might include things such as the size and diversity of the population for which the administrative data exists, the methods used for data collection (e.g. whether hospital records are self report or reported on behalf of someone else) and what information is gathered about an individual or business. Limited opportunity to influence the business processes underlying the creation of administrative data can have a significant impact on the quality of the resulting statistics produced, particularly their relevance, accuracy and coherence.

The decision to use administrative data should rest on an assessment of whether the noise generated in the data by the business processes that created them are of an acceptable level in relation to what the data are supposed to represent. 'Noise' generated refers to the measurement errors which have an impact on the quality of data by distancing the data from what they actually represent. For example, 'noise' may happen because of a transcription error that is not fixed prior to data being used, so an answer of twenty three point five (23.5) is recorded as thirty two point five (32.5).

There is also the cost benefit trade-off of spending money and effort to influence and change the up-stream process, e.g. convincing organisations to provide electronic data files. This needs to be considered in regards to the efficiencies to be gained and the ability to trust that the agreed processes have been undertaken.

Influencing data custodians can be a very difficult task and they may want compensation for any changes to systems that are designed to capture data in a more efficient way for the receiving agency.