Standards for Statistical Releases
This guidance sets out the Statistics Authority’s views on what constitutes a good Statistical Release. It is based on the proposals contained in the Statistics Commission report Releasing Official Statistics (2008)[1] and the requirements of the Code of Practice for Official Statistics published in January 2009.[2] This document will be updated over time and revised versions will be published on the Authority’s website.
Statistical Releases are summary documents issued when new National Statistics data are first published, or when a new compendium of statistics is published. They will normally be available on the National Statistics Publication Hub.
1. Identify the statistics being released and their status
Include:
1.1 A title that describes the coverage of the release and the point in time or period to which the latest statistics relate.
1.2 A statement about the frequency of the release (annual, quarterly, etc.) and the frequency with which the data are compiled/updated.
1.3 Standard headings, formatting, logos etc to be used for all National Statistics releases, as directed by the National Statistician.
1.4 The name of the originating department or agency, and contact details for the responsible statistician.
1.5 A brief account (near the start of the release) of what is included in the release in terms of tables and subjects discussed.
1.6 Identification of which statistics in the release are new.
2. Include commentary that is helpful to the non-expert and presents the main messages in plain English.
Include:
2.1 A summary that identifies the main messages - those points that the informed reader would regard as the most interesting and relevant to public debate about the subject of the statistics; no more than four or five points.
2.2 Language that is straightforward and widely understood and does not need to be ‘translated’ by journalists or commentators into simpler English. Where technical terms cannot be avoided, they should be explained in the text, not just in a footnote.
2.3 Explanation of the statistics, which goes further than simply describing rises and falls. Provide a narrative that brings to life the messages contained in the statistics, making suitable comparisons - over time, between areas within the country, and internationally. Use graphs, tables and maps to illustrate these comparisons. In addition, explain why the statistics are important, to whom, and for what they are likely to be used.
3. Use language that is impartial, objective and professionally sound.
Include:
3.1 Text that is impartial, avoids statements of opinion and is demonstrably evidence-based. It should not give the impression that it either endorses or criticises current or past government policy.
3.2 Descriptive statements that are demonstrably consistent with the statistics.
3.3 Description of proportions, changes, trends, patterns etc that are professionally sound. Sampling and non-sampling variability should be discussed in the text, and confidence intervals included and explained where meaningful.
4. Include information about the context and likely uses.
Include:
4.1 Factual information about the policy or operational context in which the statistics have been collected and will be used; including whether the statistics are used to monitor government targets and what they show in the context of those targets. It is appropriate to identify targets and policies in factual terms; it is not appropriate to comment on them or their impact.
4.2 Comment on the quality and reliability of the statistics in relation to the range of potential uses. It is appropriate to make cautious, speculative comments about the uses to which people are likely to put the statistics.
5. Include, or link to, appropriate metadata
Include or link to:
5.1 Information about sources, methods, definitions and reliability; and, where applicable, information about how the methods and definitions used relate to European Union or international concepts and classifications.
5.2 An indication of comparability with other similar data, particularly with other parts of the UK where data cover only one of the UK countries.
5.3 Where data definitions or methodology have recently changed, adequate description of these changes, including numerical comparisons that enable users to see the extent of differences with the previous data series.
5.4 Where data are normally subject to later revision, a clear explanation that these are initial estimates and when they are likely to be revised.
