2021 Census dissemination planning
What's new?

Release date: May 12, 2021

Overview

Evaluating and revising the content of the 2021 Census of Population questionnaire through content consultations and the 2019 Census Test ensures the continued relevance of the census. Census information is used to make decisions at the community-level, provincial and territorial level, and the country as a whole.

2021 Census of Population content changes

For information on content changes, please access the series of fact sheets which offer an overview of content changes for the 2021 Census. These concise documents explain why new and modified questions are asked and describe the changes considered along with the resulting approach for 2021. There are five fact sheets on new and modified content and one fact sheet on the 2019 Census Content Test: Design and methodology.

Please note that content changes will be reflected in the disseminated content of the 2021 Census of Population product and service line.

New quality indicators for data from the 2021 Census of Population

For the 2021 Census of Population, the dissemination strategy for the quality indicators has been completely revamped with the aim of providing more detailed information about data quality. New quality indicators will be included with the data products, helping users to better assess the data quality and determine how well the available information meets their needs.

What's changed?

  1. New main quality indicator for each geographic area

    Previously, the main data quality indicator for each geographic area was the global non-response rate (GNR). The GNR combined total non-response (when all questions are not answered for a dwelling) and partial non-response (when only some questions are not answered). The total non-response (TNR) rate, the main quality indicator that will now be used with every 2021 Census of Population product released, will only factor in total non-response. Information about partial non-response will now be provided separately for each question.

    Disaggregating information on non-response will help users to better identify data that could potentially be affected by non-response bias. Non-response leads to bias when the characteristics of respondents and non-respondents differ. For a given profile of non-respondents, a lower TNR rate indicates a lower risk of non-response bias and, therefore, more reliable figures and estimates.

  2. New quality indicators by question available for lower-level geographic areas

    Quality indicators by question were developed for the 2021 Census of Population: non-response rates and imputation rates.

    The non-response rate by question will now be available for lower-level geographic areas, such as census subdivisions (CSDs). This indicator will provide a measure of partial non-response. A lower non-response rate by question indicates a lower risk of bias for the estimates derived from a particular question. When used together with TNR rate, users can measure the extent of non-response for a given question.

    The imputation rate by question will now be available for lower-level geographic areas such as CSDs. This indicator will provide a measure of how much processing was done on the data during the edit and imputation process put in place to manage non-response and some inconsistencies observed in the data.

  3. New variance-based quality indicator for long-form estimates

    Confidence intervals will be available for the majority of the long-form estimates. This indicator will provide a measure of the accuracy of the long-form estimates. It will help users to easily make a correct statistical inference. Using a science-based approach, research and simulations have been done to ensure that these confidence intervals are constructed using adequate statistical methods for the data and areas of interest for the Census of Population.

  4. Quality indicators available in data tables

    For the first time, the main data quality indicators will be available in data tables with the exception of confidence intervals in disaggregated data tables with a very large number of cells and multi-cycle tables. Users will therefore be able to use them with the census counts and long-form estimates. Previously, some quality indicators were available only in the reference products.

More information

If you would like to know more about what's new, please email us at 2021 Census consultation.

Report a problem on this page

Is something not working? Is there information outdated? Can't find what you're looking for?

Please contact us and let us know how we can help you.

Privacy notice

Date modified: