Statistical notice on revision to postcode areas in claims made and starts to Universal Credit
Published 11 August 2020
© Crown copyright 2020
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/universal-credit-statistics-revision-to-postcode-areas-in-claims-made-and-starts/statistical-notice-on-revision-to-postcode-areas-in-claims-made-and-starts-to-universal-credit
Summary
Postcode areas for claims made and starts to Universal Credit have been revised. This affects statistics for claims made in the period 13 March 2020 to 9 April 2020 and for starts to Universal Credit for April 2020. This is due to more data becoming available, improving the accuracy of the statistics.
Methodology
Postcodes for claims made and starts to Universal Credit are taken from an extract of Universal Credit full service data shortly after the count date, the 2nd Thursday of the month. Where a postcode is not available on the extract, a postcode is imputed for that claim based on the distribution of known postcodes. This is usually fewer than 5% of claims having an imputed postcode.
Issue
For claims made on and after the 13 March 2020, the postcodes for around 90% of claims were not available in the data extract used to produce the statistics for the publication on the 18 May 2020. This meant that postcodes were imputed for around 90% of claims. This was not identified at the time of production for the May publication.
These postcodes are now available. Due to the large proportion of imputed postcodes, and the differences in aggregate totals for postcode areas this produces from actual totals, the affected periods have been revised.
Impact
The additional data causes revisions in number of claims made in individual postcode areas range from -41,984 (Manchester) to 16,600 (South West London).
The revisions to postcode areas for starts are between -13,331 and 6,016, with 84% of postcode areas being revised by +/- 2,500.
Table 1: Number of postcode areas by size of revision
| Size of revision | Number of postcode areas for claims made | Number of postcode areas for starts |
|---|---|---|
| -10,000 and under | 11 | 1 |
| -10,000 to -5,000 | 8 | 5 |
| -5,000 to -2,500 | 6 | 10 |
| 2,500 to 0 | 15 | 21 |
| 0 to 2,500 | 33 | 70 |
| 2,500 to 5,000 | 20 | 12 |
| 5,000 to 10,000 | 25 | 1 |
| Over 10,000 | 2 | 0 |
Why does this not affect People and Households on Universal Credit?
The issue does not affect People on Universal Credit or Households on Universal Credit. These 2 data series use postcodes from a different data source. Claims made and Starts do not use this data source as it requires the National Insurance number (NINo) to be available to be able to match to the dataset. NINo is not always available for claims made before identity has been verified.
Improvements to quality assurance
Quality assurance is being improved to identify when a large number of postcodes are being imputed.
Contact
Statistician: Stephen Slater
Email: team.ucos@dwp.gov.uk
Media enquiries: DWP Press office on 0203 267 5129