Census 2021 outputs: content design and release phase proposals

Closes 5 Oct 2021

Section 7: Paradata

Paradata refer to information about how we collected and processed the data. They’re separate from the statistical data that we produce from the census.

In line with 2011 and previous censuses, we will publish a General Report that will provide an overview of the complete census operation. Ahead of that, we propose to publish some high-level paradata about how people completed their census returns.

We expect to publish information broadly similar to what was included in the 2012 Providing the online census publication and available on our How did we do in 2011? page. We’re planning to include information on how people completed the census, such as the share of responses online and on paper, within our initial publications. We’re also planning to include information about how people used our digital services. These are scheduled for publication in late 2021.

As for the 2011 census, we will release some information, such as household return rates, at local authority level. Return rates are the number of household questionnaires returned as a proportion of the total valid household addresses that were not identified as vacant. We used return rates during the census field operation to target field staff resources to the lowest responding areas.

We’re looking at how demographic data from the census can be used alongside this operational paradata. We want to understand if there’s a data user need for us to produce more detailed information on:

  • household and individual response rates
  • mode and language of response
     

Household and individual response rate

The household response rate is the total number of households whose details were completed on a returned questionnaire, divided by the estimate of the total number of valid non-vacant households.

The individual 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.

Following the 2011 Census, we published household and individual response rates by variables such as age and sex. We could replicate this for 2021 data and also produce other cross-tabulations.

We’d like to know what needs you have for paradata on household and individual response rates.

Mode and language of response

The mode of response is information on whether the response was submitted online, on paper or through another means. Other means include telephone capture or assisted digital.

Following the 2011 Census, we published data on the proportion of returns made by mode: online or paper. For 2021, we could add a third category, which includes all other modes of response. We’re also looking into how we can derive a new digital propensity index based on how likely households were to respond to Census 2021 online.

For Wales, as well as mode of response, we can provide information on language of response. This information will depend on whether it was a paper or online response.

For paper responses, we can produce information on whether respondents used the Welsh language form or the English language form.

For online responses, we can produce information on which language the form was set to at the point of entry and the point of submission. These include:

  • started form in Welsh and submitted in Welsh
  • started form in Welsh and submitted in English
  • started form in English and submitted in Welsh
  • started form in English and submitted in English
     

If a user need is evidenced, and these are produced, we would publish them after the main census release of data for the same characteristics and geographies.

We’d like to know what needs you have for paradata on mode and language of response.