Following the release of a Census file, the RDC program experiences a high volume of data access applications. Please anticipate longer than average review times for proposal approvals.
Please include the following information in Census/NHS proposals:
- Clearly explain the topic being examined and use specific terms (e.g. demographic research by way of variables related to age, sex, marital status and language)
- List the census years required
- Describe the level of geography required including the lowest level (e.g. census tract)
Providing this detailed information will facilitate the timely evaluation of the proposal
- For the 2011 National Household Survey, tabular output at the Dissemination Area (DA) is not allowed
- Concepts change over time and researchers should expect some variations in variable definitions between censuses (and the NHS). Please consult the appropriate documentation
- Researchers should review with their RDC analyst the confidentiality vetting guidelines associated with the census and NHS
Additional information for the 2011 Census and 2011 National Household Survey (NHS)
When applying for RDC access to the 2011 Census or the 2011 NHS, researchers should consider how these files differ.
The 2011 Census was a mandatory questionnaire sent out to all private and collective occupied dwellings. It had a final national response rate of 97%. The Census enumerated the entire Canadian population and Canadian citizens and landed immigrants who were temporarily outside the country on Census Day. Information was collected on demography, family and family composition, dwellings and language. The RDC Census file comprises a sample of 20% of all households from the 2011 Census. (The entire Census master file was not made available to the RDCs). The 20% sample represents just over 7.5 million respondents. Census geography variables ranging from the province to the dissemination area are included in the file. The Census file is hierarchical allowing for analysis of 5 distinct levels: persons, census families, economic families, households and dwellings. Weights are included in the file to enable calculation of estimates for the total population.
The 2011 National Household Survey (NHS) was a voluntary questionnaire which replaced the former mandatory (e.g. 2006) Census long-form questionnaire. The sample frame was one-third of all Canadian households and achieved a response rate of 69%. Unlike the Census, Canadian citizens and landed immigrants living outside the country were excluded from the NHS (Collectives were also excluded). The NHS collected information from households on a wide range of topics including labour market activities, education, income, dwellings, place of birth and immigration, Aboriginal populations, ethnicity and visible minority status, journey to work, religion, activity limitations, and mobility. It is important to note that there is overlap between the 2011 Census and NHS master files in that all of the variables contained in the Census (demography, family and family composition, dwelling and language) are also available in the NHS. The NHS master file has just over 6.7 million respondents. It includes most levels of census geography ranging from the province to the dissemination area. Like the Census, the 2011 NHS master file is hierarchical allowing for analysis of 5 distinct levels: persons, census families, economic families, households and dwellings. Two composite weights are included in the master file to enable calculation of estimates for the total population living in private households.
Comparing the Census and NHS
It is possible that differences exist between the 2011 Census counts and the NHS estimates. Two reasons can explain these differences:
- The definition of the population of each data source: the target population for the 2011 Census includes usual residents in collective dwellings and persons living abroad, whereas the target population for the NHS excludes them.
- The variability of the estimates for the NHS: the NHS estimates are derived from a sample survey and are therefore subject to sampling error; they are also subject to potentially higher non-response error than in the census due to the survey’s voluntary nature.
Comparing the Census sample and the published counts
It is also possible that differences exist between the 2011 Census counts and the estimates obtained with the Census sample. They are due to sampling error.
Any form of record linkage or matching of respondents between the 2011 Census and 2011 NHS RDC master files is not possible or permitted.
Contact your local RDC for further information and public documentation relating to the Census and NHS.