The GSS Quality Task Force was established in 2010 to develop and draft proposals for statistical quality policies, standards and good practice associated with:
quality measurement and reporting
This document sets out guidance developed by the Task Force to help producers of official statistics achieve the quality requirements of the Code of Practice for Official Statistics as assessed by the UK Statistics Authority. It concentrates in particular on Principle 4 (sound methods and assured quality) and supplements the National Statistician’s Guidance on Quality, Methods and Harmonisation (see External Links).
1. What does quality mean?
The GSS Quality Task Force has agreed definitions of key quality terms as used in the context of Official Statistics. These definitions have been signed off by the GSS Statistical Policy and Standards Committee. Key terms are:
Quality – 'Fitness for purpose'
Quality Management – 'encompassing approach to quality work'
Quality Assurance – 'anticipating and avoiding problems'
Quality Control – 'responding to observed problems'
For more details please see 'Key Quality Terminology' under Related Links.
2. Good Practice
On the basis of the Code of Practice, (particularly Principle 4), the GSS are required to:
o engage in quality management
o engage in quality assurance
o review their statistical processes
o measure and report on the quality of their outputs
This document recommends good practice in terms of meeting these requirements.
2.1 Quality Management and Quality Assurance (including continuous improvement)
Principle 4, Practice 4
'Publish quality guidelines, and ensure staff are suitably trained in quality management.'
Principle 4, Practice 3
'Adopt quality assurance procedures …'
Principle 4, Practice 5
Seek to achieve continuous improvement in statistical process …'
A training course has been developed that reviews the key elements of quality management and quality assurance (specifically addressing the requirement in Principle 4, Practice 4). This course is available at two levels: one aimed at senior managers (strategic emphasis) and one aimed at other GSS staff (operational emphasis). Please see 'GSS Training in Quality Management and Quality Assurance' under Related Links for more information on the courses.
2.2 Quality Reviews
Principle 4, Practice 1
'Ensure that official statistics are produced according to scientific principles. Publish detail of the methods adopted, including explanations of why particular choices were made.'
Principle 4, Practice 5
'Seek to achieve continuous improvement in statistical processes by, for example, undertaking regular reviews or releasing statistical work in progress, such as experimental statistics.'
The Quality, Methods and Harmonisation Tool (QMHT) is a self-assessment questionnaire, designed to aid producers of statistics in reviewing their surveys and outputs. As such, it helps them work towards becoming compliant with the Code of Practice for Official Statistics. QMHT covers all stages of the statistical process, and is suitable for survey and administrative data. Please see 'Quality, Methods & Harmonisation Tool' under Related Links for details.
2.3 Measure and report on quality
Principle 4, Practice 2
'Ensure that official statistics are produced to a level of quality that meets users’ needs, and that users are informed about the quality of statistical outputs …'
Principle 4, Practice 4'Publish quality guidelines …'
Principle 8, Practice 1
'Provide information on the quality and reliability of statistics in relation to the range of potential uses, and on methods, procedures, and classifications.'
A means of measuring quality and ensuring that the above practices are considered is provided in the Quality Measurement and Reporting Guidance. This draws together pre-existing guidance and provides information on good practice, including examples and case studies and can be found in 'Quality Measurement and Reporting Guidance' under Related Links.
Heads of Profession have responsibility for ensuring that the Code of Practice is observed within their departments. This document, its annexes and the training offered on quality management are effective tools to start the implementation and further development of this good practice within each department.
European Statistical System ( ESS ) Quality Dimensions
There are six European Statistical System (ESS) dimensions of output quality, which are in place to ensure the fitness for purpose of a statistical product. These dimensions are: relevance, accuracy, timeliness and punctuality, accessibility and clarity, comparability, and coherence.
For the purposes of quality reporting, for example in the ESS Handbook for Quality Reports, the dimensions of comparability and coherence are sometimes combined, as there are obvious links between these two dimensions in terms of reporting. These dimensions are also grouped in the Quality Measurement and Reporting guidance that has been produced by the GSS Quality Task Force.
More recently, Eurostat has added four principles, which are: output quality trade-offs; user needs and perceptions; performance cost and respondent burden; and confidentiality, transparency and security. These are not dimensions, but are useful principles to consider when reporting on quality, so they are also included in the Quality Measurement and Reporting guidance.The above grouping and additional considerations explain why the number of ESS quality dimensions varies between some of the outputs of the GSS Quality Task Force. There are six ESS dimensions of output quality, but for the purposes of quality reporting these are grouped into five dimensions plus the four principles for consideration.