The Canadian Census always has two mandatory census forms: the short form - sent to all Canadian households - and the long form - sent to 20% of Canadian households - except for the 2011 Census, which only had a mandatory short form. The questions that were traditionally asked in the mandatory long form were moved to a new voluntary National Household Survey (NHS), with the exception to this is the language questions, which were added to the mandatory short form. This change made the data collected in the 2011 Census and NHS far less reliable and accurate. It is essential to be aware of the limitations of the 2011 Census when using and analyzing the data from it.

There are differences in methodology between a mandatory census and a voluntary survey, and students, researchers, and policy makers need to be aware of the following when using and interpreting NHS data.

• 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 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.
• Caution should be used when comparing NHS data to the 2006 Census or earlier censuses, especially when it comes to data for small geographies. See "Comparability of the NHS estimates" in the National Household Survey User Guide for more information. Both subsections, "Comparability of the NHS estimates and the 2006 Census" and "Discrepancy between 2011 Census counts and 2011 NHS estimates" are important when considering the quality and comparability of the data.
• Pay attention to the Global Non-Response Rate. The higher the rate, the greater the risk of non-response bias. 
• Note that Statistics Canada has not released any data for geographic areas with a global non-response rate of 50 percent or higher. See the Geographic areas not released page. Of particular interest for many students and researchers at UNBC will be the list of the BC census subdivisions (CSDs) for which data was not released. (To determine the reason for data suppression, click on the notes in the "Reason for no release" column.)

As you review the above links, think about the implications for your geography. For instance, if your geography has a global non-response rate of 49.9, you might want to discuss possible issues with the data in your report. The nature of your community (for instance, the extent of homogeneity of the population) will have a bearing on how serious these issues might be.

Note: If you have chosen a geography where the data has been suppressed due to a global non-response rate of 50 percent or higher, it is still possible to access the data. Whether or not you will want to do so will depend upon your conclusions regarding the quality of the data based on the above information.

Some links for those interested in the history of the decision to move from a mandatory long-form census to a voluntary survey:

• CensusWatch (datalibre.ca) -- Many of the entries in these lists include links to the actual letters written in opposition and in support of the decision.   
• CHANGING THE LONG-FORM CENSUS—ITS IMPACT ON WOMEN’S EQUALITY IN CANADA: Report of the Standing Committee on the Status of Women.
• CBC Radio's The Current: Sept. 9, 2010 interview with Munir Sheikh, former Chief Statistician with Statistics Canada.
• Globe & Mail editorial, July 27, 2010.
• Opinion piece by Paul Saurette, Associate Professor of Political Studies, University of Ottawa.
• Globe & Mail article, Oct. 6, 2011 related to a study commissioned by Statistics Canada.
• And, a little humour courtesy of Rick Mercer.

Consequences:

• Piece by Toronto Star columnist Carol Goar, Oct. 7, 2014.

Since the Oct. 19, 2015 election:

• Globe & Mail article, Oct. 21, 2015 about interviews with two former chief statisticians of Statistics Canada regarding the feasibility of reinstating the mandatory long-form census in time for the 2016 Census.