Cancellation of the mandatory long-form census - background and impact

On July 13, 2010, Minister of Industry Tony Clement announced that the 2011 mandatory long-form census would be abolished, and replaced with a voluntary survey instrument (the National Household Survey or NHS). On July 21, 2010, Munir Sheikh, the Chief Statistician of Canada, resigned from his post asserting the advice presented by Statistics Canada to Minister Clement was misrepresented as backing the government's decision. In his letter of resignation, Mr. Sheikh wrote:

"I want to take this opportunity to comment on a technical statistical issue which has become the subject of media discussion ... the question of whether a voluntary survey can become a substitute for a mandatory census. It can not."

In the run-up to the abandonment of the 2011 mandatory long-form census, concerns were expressed by academics, library groups, think tanks, government advisory boards, politicians, business groups (and others) that the data produced from a voluntary survey would be less reliable than from the Census, and would be difficult to compare to previous data.
The 2011 National Household Survey (NHS) had a 68.6% response rate, as opposed to 97.1% for the 2011 Census. As a consequence of the voluntary nature of the NHS, when the 2011 NHS data was published, Statistics Canada found it necessary to suppress data for 1,128 census subdivisions (townships, towns, villages, Indian reserves, etc.) where the Global Non-Response Rate (GNR: effectively, the failure to complete the questionnaire) was above 50% (a higher threshold than used in the Census). For Canada, the GNR was 26.1%. The map below shows the suppressed census subdivisions (CSDs) in black.

  Map of Canada, showing CSD Suppression

An example map created by the Western University Libraries Map and Data Centre illustrates the problem further. The map shows GNR by dissemination area (DA) for the city of London. City-wide, the GNR was 24.3%. Twenty-six dissemination areas recorded GNR of 50% or higher (with a maximum of 76.1%): the NHS User's Guide indicates that "the estimates for such areas have such a high level of error that they should not be released under most circumstances". A further two hundred seventy-six DAs recorded a GNR of 30 to 50%. While Statistics Canada has created estimates for each DA (based in part on responses to the mandatory long-form from the 2006 Census), how closely the estimates match the reality of each DA is uncertain as a consequence of non-response.

Aside from data suppression, Statistics Canada notes in the NHS User Guide that the data may not be comparable to the previous (2006) long-form Census:

"Caution must be exercised when NHS estimates are compared with estimates produced from the 2006 Census long form, especially when the analysis involves small geographies. Users are asked to use the NHS's main quality indicator, the global non-response rate (see Section 6.3), in assessing the quality of the NHS estimates and determining the extent to which the estimates can be compared with the estimates from the 2006 Census long form. Users are also asked to read any quality notes that may be included in dissemination products. "

The realized predictions of less comparable and reliable data are illustrated by the following examples.
  1. The release of immigration data from the NHS announced that the largest source of immigrants to Canada in the past five years was the Philippines - a finding at odds with the immigration records collected by Citizenship and Immigration Canada. Statistics Canada acknowledged:

    "This result was not in line with administrative data from the Department of Citizenship and Immigration Canada which provides the number of recent immigrants by their country of birth settling in Canada each year. A number of factors could explain this difference, such as the effects of sampling, response patterns, and under or over estimation of certain groups of recent immigrants in the NHS."

  2. In the Income Reference Guide, Statistics Canada notes:

    "Given the sensitivity of most income indicators to such methodological differences, users should use caution when comparing income estimates from the NHS to other household income surveys, administrative data or 2006 Census data or earlier censuses."

    Some researchers have questioned the reliability of the NHS, calling for the income data to be withdrawn. These SSHRC-funded researchers compared income data from the NHS to tax-filer data from the Canada Revenue Agency, and declared that:

    "The income data in the National Household Survey is not valid. It should not be used or cited. It should be withdrawn. The 2016 census should be restored to the non-politicized, non-partisan scientific methodology that existed prior to the flawed 2011 National Household Survey."

 

Current process in Parliament to reinstate the mandatory long-form census for 2016

Back to Mandatory Long-form Census