Census of Population

Detailed information for 1996

The census is designed to provide information about people and housing units in Canada by their demographic, social and economic characteristics.

Data release - April 15, 1997

• Questionnaire(s) and reporting guide(s)
• Description
• Data sources and methodology
• Data accuracy
• Documentation

Description

Statistics Canada conducts the Census of Population in order to develop a statistical portrait of Canada and Canadians on one specific day. The census is designed to provide information about people and housing units in Canada by their demographic, social and economic characteristics.

The Census of Population is a reliable basis for the estimation of the population of the provinces, territories and local municipal areas. The information collected is related to more than 80 federal and provincial legislative measures and provides a basis for the distribution of federal transfer payments. The census also provides information about the characteristics of the population and its housing within small geographic areas and for small population groups to support planning, administration, policy development and evaluation activities of governments at all levels, as well as data users in the private sector.

Clients: Federal government, provincial and territorial governments, municipal governments; libraries; educational institutions; researchers and academics; private industry; business associations labour organisations; ethnic and cultural groups; private citizens; public interest groups.

Subjects

• Commuting to work
• Education, training and learning
• Employment and unemployment
• Families, households and housing
• Globalization and the labour market
• Immigration and ethnocultural diversity (formerly Ethnic diversity and immigration)
• Income, pensions, spending and wealth
• Indigenous peoples (formerly Aboriginal peoples)
• Industries
• Labour
• Languages
• Occupations
• Population and demography
• Population estimates and projections
• Unpaid work

Data sources and methodology

Target population

The census enumerates the entire Canadian population, which consists of Canadian citizens (by birth and by naturalization), landed immigrants, and non-permanent residents together with family members who live with them. Non-permanent residents are persons living in Canada who have a Minister's permit, a student or employment authorization, or who are claiming refugee status.

The census also counts Canadian citizens and landed immigrants who are temporarily outside the country on Census Day. This includes federal and provincial government employees working outside Canada, Canadian embassy staff posted to other countries, members of the Canadian Armed Forces stationed abroad, and all Canadian crew members of merchant vessels. Because persons outside the country are enumerated, the Census of Canada is considered a modified de jure census.

Sampling

This survey is a census with a cross-sectional design.

The long Census form (2B) is collected on a sample basis. The approach used in sampling areas is a systematic 1 in 5 sample selection of households. Initially, the weight for each sampled household is simply 5 - because a 1 in 5 sample was selected.

However, although we know the sample contains almost one-fifth of all dwellings, we cannot be certain that all sub-groups (such as males aged 20 to 24) will be properly represented. To ensure that the most important sub-groups are consistently estimated, a weighting procedure known as "two step generalised least squares estimation procedure" is used. This method constrains the sample weights to known population counts for the most important sub-groups for both the collection unit (known as the Enumeration Area) and for a larger geographic unit (known as the Weighting Area). The estimation method will adjust the initial household weight as little as possible. (For more information, see the 1991 Census Technical Report on Sampling and Weighting, Catalogue 92-342.)

The weighting method produces fully representative estimates from the sample data. In 1996, weighting was done by a method known as calibration or regression estimation. Calibration estimation starts with initial weights of approximately 5 and then adjusts them by the smallest possible amount need to agreement between the sample estimates (eg. number of males, number of people aged 15 to 19) and the actual population counts.

Data sources

Data collection for this reference period: 1996-05-14 to 1996-07-31

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

This stage of the census process ensured that each of the 10.9 million dwellings in Canada was enumerated.

To ensure the best possible coverage, the country is divided into small geographic areas called enumeration areas (EAs). Each census representative is responsible for at least one EA. The optimal number of households in an EA ranges from 125 in rural areas to 440 in urban areas. In the 1996 Census, there were 49,361 enumeration areas in Canada, and 38,000 people engaged in collecting the data.

(a) Self-enumeration: In 1996, census representatives dropped off census questionnaires at approximately 98% of households. These households were asked to complete the questionnaire themselves on May 14, and mail it in.

(b) Interview: Roughly 2% of households were enumerated by interview; in other words, a census representative visited the household and completed the questionnaire during an interview. This method was used in remote and northern areas, and on most Indian reserves. It was also used in the town centres of large urban areas, where residents are more difficult to enumerate. In addition, some remote northern areas were enumerated in February and March of 1996. This advance census was carried out in areas where communities disperse in the spring and migrate to their hunting and fishing grounds.

View the Questionnaire(s) and reporting guide(s).

Error detection

The questionnaires underwent an initial manual edit during collection. Field staff reviewed them for missing responses or unacceptable multiple responses. Such problems were resolved by contacting the respondents and obtaining the required information. In addition, some basic structural edits were done in HOP, where the questionnaires and the visitation records were referred to as necessary.

The final clean up of the data was fully automated. It involved applying a series of detailed edit rules, which identified missing or inconsistent responses. These missing or inconsistent responses were corrected by changing the values of as few variables as possible through imputation.

Imputation

Imputation was done using either a "deterministic" or a "minimum change hot deck" method. For deterministic imputation, errors were corrected by inferring the appropriate value from answers to other questions.

For minimum change hot deck imputation, a record was selected that had a number of characteristics in common with the record in error. Data from this "donor" record were borrowed and used to change the minimum number of variables necessary to resolve all the edit failures.

Estimation

The Generalised Least Squares Estimation Procedure (GLSEP) is used to produce the census estimates. The GLSEP reduces the standard errors of the sample estimates and ensures that the estimates agree with known population counts. Weights are calculated at the household level.

Quality evaluation

Please refer to attached link below:

• Additional documentation

Disclosure control

Statistics Canada is prohibited by law from releasing any data which would divulge information obtained under the Statistics Act that relates to any identifiable person, business or organization without the prior knowledge or the consent in writing of that person, business or organization. Various confidentiality rules are applied to all data that are released or published to prevent the publication or disclosure of any information deemed confidential. If necessary, data are suppressed to prevent direct or residual disclosure of identifiable data.

In all products released, procedures are applied to prevent the possibility of associating statistical data with any identifiable individual: the data are randomly rounded and they are suppressed for certain geographic areas. Random rounding is a method whereby all figures in a tabulation, including totals are randomly rounded (either up or down) to a multiple of "5", and in some cases "10". This technique provides strong protection against direct, residual or negative disclosure, without adding significant error to the census data. However, figures on population counts only are not rounded since they provide no information on the characteristics of these populations.

Area suppression results in the deletion of all characteristic data for geographic areas with populations below a specified size. All data for standard and non-standard geographic areas with a total population of less than 40 persons are suppressed. If the data contain an income distribution, those areas with a population below 250 persons are suppressed. For postal code geography, the three-character forward sortation areas will be suppressed using the 40-person rule. For the six-character local delivery units, a 100-person suppression rule will be used. In all cases, suppressed data are included in the appropriate higher aggregate subtotals and totals.

Revisions and seasonal adjustment

This methodology does not apply to this survey.

Data accuracy

An assessment of the quality, comparability and limitations of the 1996 Census data is carried out as an integral part of release and dissemination activities. All variables are certified before release by way of a set of brief studies designed to judge the consistency of the data with that of previous censuses and that of alternate data sources. This process is augmented by measures of data quality provided by evaluation studies. The data quality evaluation studies are directed beyond the immediate certification objectives. They provide indications of the quality of the census data from the source of error - coverage, response, non-response, processing and sampling - and of the impact on individual variables. The result of these studies, along with the certification analysis, will be integrated into a series of technical reports.

The basic unit used in the calculation of the response rate is the household. (This includes private and collective households, 2Cs, random additions for misclassified vacants and Form 4 households. It excludes unoccupied dwellings and dwellings occupied only by foreign or temporary residents. ) In the 1996 Census, there were 10,803,628 in-scope households on the database, of which 88,641 were total non-response (Form 4) households. There were 10,714,987 households with at least some data. The overall response rate was therefore 10,714,987 / 10,803,628 = 99.18%.

Documentation

• Census Web Site
  - For all census documentation, please refer to the following address: http://www12.statcan.gc.ca/census-recensement/index-eng.cfm
  • Format: Census Web Site - HTML[HTML]