The census is the most complete source of information about the population that we have. Every effort is made to include everyone. It is the only survey which provides a detailed picture of the entire population, and is unique because it covers everyone at the same time and asks the same core questions everywhere. This makes it easy to compare different parts of the country.
However no census is perfect and some people are inevitably missed. ONS therefore uses complex statistical techniques to adjust the 2011 Census counts for those people missed by the census. The methods and quality assurance approach was researched and developed in consultation with academics, statisticians, demographers and users of census data. The result was a suite of methods to process, clean, adjust and protect the census results.
Quality and Methodology information paper (177.6 Kb Pdf) – July 2012. This document provides a range of information that describes the quality of the output and details any points that should be noted when using the output.
Quality assurance
A critical part of producing the statistics is the quality assurance process which ensures that the methods have been correctly applied and that the statistics are robust and fit for purpose.
Resources available:
Quality assurance of census population estimates (1.23 Mb Pdf) : An overview of the quality assurance process with examples of how inconsistencies identified during the QA process were identified and resolved.
Quality assurance results by local authority: The 2011 Quality Assurance Pack is an Excel tool that contains local authority quality assurance information which replicates the age-sex charts which were used in the quality assurance assessment of each local authority. A guidance note on the use of the packs is also available.
Results from using routinely-collected government information (694.5 Kb Pdf) for 2011 Census quality assurance.
Assessment of the Longitudinal Study - 2011 Census linkage. Using a bespoke dataset, the report compares linkage rates at each census from 1981 onwards, examines the demographic of those individuals in the LS but not in the census, and includes data on those enumerated more than once in the 2011 census. Download the linkage report (488.4 Kb Pdf) .
Quality measures
Quality measures help users understand the quality of the 2011 Census results:
Response and imputation rates:
Response rates - the total number of usual residents whose details were completed on a returned questionnaire, divided by the estimate of the total number of usual residents. Prior to the census, ONS set a headline target of achieving 94 per cent response for England and Wales overall. Also includes coverage rates and return rates.
Item non-response - where respondents sometimes make errors when recording their answers, resulting in data that were not valid for estimation and analysis.
Item imputation - the process which corrected for any missing responses or inconsistencies.
Other quality measures:
Confidence intervals - indicators of the extent to which the estimate may differ from the true population value. The larger the confidence interval, the less precise is the estimate.
Assessing the accuracy of responses (Census Quality Survey CQS) report helps users understand the strengths and limitations of the 2011 Census data and how to use them appropriately.
Data capture, coding and cleaning turns census returns into data that we can use to produce statistics.
Quality notes and clarifications
Quality notes and clarifications: Details of specific issues with the quality of 2011 Census statistics and clarifications of table content to aid users in understanding and interpretation of the statistics. This will be updated on a regular basis. See also 2011 Census Products: Issues and corrections and Comparability over time.
How census compares with other data sources
Files providing information about the difference between the census and other datasets, available to download:
Resources available:
Explaining differences between 2011 Census estimates and rolled-forward mid-year population estimates (361.9 Kb Pdf) : A paper explaining the differences and an Excel file (257.5 Kb Excel sheet) containing the rolled-forward 2011 mid-year population estimates.
Comparison between 2011 Census estimates and the GP NHS Patient Register (66.2 Kb Pdf) : A paper describing the comparisons of census estimates and Patient Register counts by sex and broad age groups by local authority, region and nationally, and an Excel file (248.5 Kb Excel sheet) containing the comparisons.
Statistical disclosure control methods
Census data provide great detail, while protecting the confidentiality of the individual. Statistical disclosure control has been applied to 2011 Census data to protect the attributes of an individual.
ONS has used two complementary strategies for protecting individuals while minimising damage to the results:
targeted record swapping, and
restriction of detail particularly at low level geographies.
Downloads:
Statistical disclosure control for 2011 Census (184.7 Kb Pdf)
Statistical Disclosure Control for 2011 UK censuses (59.9 Kb Pdf)
Confidentiality Protection Provided by Statistical Disclosure Control (76.9 Kb Pdf)
Coverage assessment and adjustment
Every effort was made to ensure everyone was counted in the 2011 Census, however no census is perfect and some people were inevitably missed. This under-enumeration does not usually occur uniformly across all geographical areas or across other sub-groups of the population such as age and sex groups.
To fill this gap, ONS developed a coverage assessment and adjustment methodology which built on the 2001 ‘One Number Census’ (ONC) approach. The methodology involved the use of standard statistical techniques, similar to those used by many other countries, for measuring the level of undercount in a census and providing an assessment of the characteristics of individuals and households missed. The approach was researched and developed over a number of years in consultation with academics, statisticians, demographers and users of census data.
An independent review of the coverage assessment and adjustment methodology took place in 2011. The review team stated that “the methods give confidence that the resulting final census population estimates will be better than any other method and will be suitable for use in resource allocation and planning”.
This section includes coverage assessment and adjustment methods and the 2011 Census Coverage Survey, and statistical disclosure control methods.
Information paper: 2011 Census Item Edit and Imputation Process (203.8 Kb Pdf): This paper outlines the methods applied to resolve item non-response and item inconsistencies in the 2011 Census data.