Skip to content

Response and imputation rates

The response rate is 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.

In 2011 the UK Census questionnaire was sent out to every home and communal establishment in the UK. As with any self completion questionnaires, respondents sometimes make errors when recording their answers, resulting in data that were not valid for estimation and analysis. This is called 'item non-response'.

Reasons for not answering correctly can be unintentional, for example where a respondent misses a question or thinks they can tick more than one option, or intentional where a respondent either does not know the answer or does not want to provide the answer.

Some correctly recorded values were considered to be invalid because they were inconsistent either with other values on the questionnaire, or with auxiliary information or definitions. For example, if a person gave their age as ten years old and gave an occupation these values were considered to be inconsistent because by definition a ten year old cannot be in employment. This is referred to as 'item Inconsistency'.

The 2011 Census data were edited in two stages to correct for item non-response and inconsistencies. A limited number of edits were applied, followed by item imputation which corrected for non-response and inconsistencies. Download the paper for definitions of 'item non-response', 'item deterministic editing' and 'item imputation', and to see how the rates have been calculated.

See also: Item edit and imputation evaluation report (819.4 Kb Pdf)  

Content from the Office for National Statistics.
© Crown Copyright applies unless otherwise stated.