DfE statistical revisions and corrections policy
Updated 30 July 2026
Applies to England
© Crown copyright 2026
This publication is licensed under the terms of the Open Government Licence v3.0 except where otherwise stated. To view this licence, visit nationalarchives.gov.uk/doc/open-government-licence/version/3 or write to the Information Policy Team, The National Archives, Kew, London TW9 4DU, or email: psi@nationalarchives.gov.uk.
Where we have identified any third party copyright information you will need to obtain permission from the copyright holders concerned.
This publication is available at https://www.gov.uk/government/publications/standards-for-official-statistics-published-by-the-department-for-education/dfe-statistical-revisions-and-corrections-policy
Overview
This statistical notice has been produced to help users of official statistics understand the reasons for scheduled revisions to official statistics and the procedure for correcting errors in official statistics in line with the Code of Practice for Statistics.
The Department for Education (DfE) aims to avoid the need for revisions to official statistics unless they are necessary. We have systems in place and robust quality assurance processes to minimise the number and scale of any unscheduled corrections.
Code of Practice for Statistics
Be transparent
3.9 Release revisions and corrections of errors transparently and as soon as possible in line with the organisation’s published policy, being clear about the nature and scale of change.
Prioritise quality
5.5 Periodically review the effectiveness of your processes and quality management approach and be open about findings and planned improvements.
Be open about quality
7.5 Give advance notice to users of planned changes to methods and sources that will impact the statistics. Explain the nature and extent of the change, and provide a consistent back series where possible.
Be clear
9.7 Give advance notice of material changes to the content of releases, such as the removal of data tables or variables, and any change in the frequency of release.
Scheduled revisions
Scheduled revisions to official statistics may happen because of changes to methods or data.
Methods changes
Planned changes in statistical methodology to improve accuracy of official statistics may lead to revisions to historical data to provide a consistent time series. Changes to methods include, but are not limited to, changes to:
- data collection systems
- administrative data sources, definitions and classifications
Where data systems and methodologies allow it, we dual-run the statistics in the first year, so that the impact of the changes on the time series is clear.
Where major changes to methods are proposed, we will, where possible, consult on the changes and announce them in advance. The scale, nature and impact of these changes will be explained alongside the statistics.
Data changes
Official statistics may be published as provisional to provide an early indication of the trend and subsequently updated when more data becomes available. This can happen when statistics use data from operational systems and not all respondents have completed the relevant information when the snapshot is taken for the official statistics publication. The historical provisional data is replaced with more accurate revised data based on a more complete response in the next publication.
Provisional data will be clearly labelled in the publication and accompanying tables. An explanation of the limitations of the provisional data, and when the final revised statistics will be published, will be included in the publication.
Unscheduled corrections
Unscheduled corrections may be a result of unexpected changes to source data or errors in statistical processing.
While there are robust procedures in place to minimise errors in our statistics systems and processes, we recognise that errors may happen occasionally. When an error is found, we will assess the impact of the error on the interpretation of the statistics and determine the appropriate response in terms of correcting the error and alerting users.
Major errors which, when corrected, would change the interpretation of data or trends that it shows will be corrected as soon as possible. The reason for the correction and its impact will be clearly shown in the publication, and known users will be notified directly where this is deemed necessary.
Minor errors, which do not change the interpretation of the data or trends, will be corrected with the next publication of the data if it is practical and cost-effective to do so. Users will be notified of minor errors in the next publication.