Table of contents
- Introduction
- Publication of rounded estimates July 2012
- Changes made to the estimates since the July publication
- The size of differences in the September and July estimates
- Consistency between 2011 Census estimates and mid-2011 population estimates
- Related internal links
- Supporting information
- Background notes
1. Introduction
On 16 July 2012, the Office for National Statistics (ONS) released the first results from the 2011 Census for England and Wales – the ‘Population and household estimates for Wales’.
This included information for unitary authorities about the usually resident population of Wales by 5-year age and sex, and also provided information on topics such as the number of households and the number of short-term residents.
On 24 September ONS has released the unrounded figures for those included in the 16 July census release. The mid-2011 population estimates published 25 September are based on the unrounded census estimates.
Back to table of contents2. Publication of rounded estimates July 2012
In the 16 July release it was necessary to round the census estimates to the nearest 100 because, at the time of publication, there remained a small number of processing stages still to be completed. By rounding to the nearest 100 the differences between the estimates published then and those published subsequently is minimal. The estimates published in July were subject to a comprehensive programme of quality assurance to give users confidence in the figures published.
Publishing rounded estimates in July allowed ONS to share the first results from the census with users and also allowed for them to be used in the production of the mid-year population estimates. These in turn can then be used in the next round of local government resource allocation.
However, ONS recognised that this might mean there would be some minor differences in the figures published in subsequent unrounded releases compared to those first published in July.
Back to table of contents3. Changes made to the estimates since the July publication
Since the July publication, processing of census data has been completed including, in particular, the statistical disclosure control process and creation of small area geography boundaries where population size has changed since the 2001 Census.
Statistical disclosure control is applied to all census estimates to ensure that no personal information is disclosed and that no individual can be identified. Rounding estimates to the nearest 100 in the July release meant that there was no risk of disclosure - allowing early publication of results before the full disclosure process was complete. Publication of unrounded estimates is only possible now that the final disclosure routines have been applied.
To account for changes in the population size of small areas since the 2001 Census a small percentage of the Output Area (OA) geography used in 2001 were updated. These Output Areas, once revised, will form the building bricks that are ‘best-fitted’ to form the higher area geographies for which 2011 Census results are published. Because these updates can only be applied once the final census population estimates are known, this stage of processing was not possible prior to the July release.
More information about the maintenance of the Output Area hierarchy for the 2011 Census will be published with look-up files and other geographical information in time for the release of small area census results.
Back to table of contents4. The size of differences in the September and July estimates
The differences between the estimates published 16 July and those published 24 September are minimal. The differences for every age/sex estimate at local authority level are always smaller than 100. In fact only three per cent of these estimates across England and Wales are different by more than 50. As the estimates in the July release were independently rounded, no local authority total is different by more than 100.
Back to table of contents5. Consistency between 2011 Census estimates and mid-2011 population estimates
The mid-2011 population estimates are based on the unrounded 2011 Census estimates. There are inevitable differences between the two final sets of estimates because they refer to different points in time and because they are based on slightly different definitions of where individuals are treated as usually resident, and consequently where they are counted.
The census estimates refer to 27 March 2011, whereas the mid-year population estimates refer to 30 June 2011. An estimate of population change has been made between these two dates to incorporate births, deaths and net migration that have occurred in the intervening period.
Differences in the definition of a resident are generally very small as they only apply to specific population sub-groups. For example, the census included armed forces personnel at their permanent family home but the mid-2011 estimates include armed forces personnel where they are stationed.
Further information about the differences in definitions used is available with the mid-2011 population estimates release that will be published 25 September.
Back to table of contents