Revisions and corrections policy

Outlines the revisions and corrections policy for census outputs.

Introduction

This revisions and corrections policy relates to the statistical outputs produced from Census 2021 by Census Office. It has been developed in accordance with the UK Statistics Authority’s requirement to publish a policy on revisions and corrections, as set out in the Code of Practice for Statistics.

Statistics may be subject to update for two common reasons:

  1. Scheduled revisions of data are planned amendments to published statistics. Initial estimates are often systematically amended to reflect more complete information as further data become available. Revisions may also be made when improvements in statistical methods or systems are made due to further investigations or the availability of additional and fuller data.
  2. Unscheduled revisions are corrections made to published statistics due to the identification of errors.

Census Office will carry out its responsibilities in respect of revisions by following this policy, which will ensure we meet the requirements of the Code of Practice for Statistics.

Scheduled revisions

Scheduled revisions are a routine part of the production of official statistics. Census Office will pre-announce any scheduled revisions and will ensure that any revisions to published census statistics are accurate, robust and freely available and that they are accompanied by the same supporting and explanatory information as are the statistics. Key outputs, subject to scheduled revisions, will have a published revisions statement.

Scheduled revisions will be categorised as follows:

R1 - To incorporate better source data such as:

  • more complete or corrected reporting by respondents
  • source data that more closely match the concepts

R2 - To reflect improved methodology:

  • changes in statistical methods
  • changes in concepts, definitions and classifications

Unscheduled corrections

While Census Office systems are designed to minimise the risk of processing error and assure the quality of source data and results, unfortunately, errors may sometimes appear in statistical outputs. Unscheduled corrections will only be made if an error is deemed substantial; a decision on whether to make a revision will be made on a case by case basis.

If an error is considered to be substantial, Census Office will act to correct statistical tables and reports, and alert stakeholders promptly. A correction notice will be provided on the website as soon as possible to inform users and ensure transparency.

If an error is assessed as having only a minor impact, the correction will be incorporated in the next planned release. Again, any revision made in this way will be clearly indicated on the website to inform users.

Labelling of revisions

The following labelling convention will be used in the publication of updates to data:

  • R1 are 'Updates'
  • R2 are ‘Improvements'
  • C are ‘Unscheduled corrections’

Contact

If you require more information about this revisions policy or would like to feedback comments, please contact census@nisra.gov.uk. We also invite comments on how users would like to be kept updated.

Review

This policy will be reviewed initially after six months of implementation and thereafter on an annual basis. The next review will take place in September 2022.