Projections of the Diversity of the Canadian Population

Detailed information for 2006 to 2031

This statistical program develops projections of the ethnocultural composition of population for Canada, provinces and Census metropolitan areas, based on various assumptions and scenarios on the components of population growth.

Data release - March 9, 2010

• Description
• Data sources and methodology
• Data accuracy

Description

This statistical program develops population projections according to some ethnocultural variables (visible minority group, generation status, place of birth, religious denomination and mother tongue) for Canada, provinces and census metropolitan areas from 2006 to 2031, based on various assumptions and scenarios on the components of population growth and differential demographic behaviors.

These projections are useful to decision makers in their planning of programs related to social cohesion, labor market integration, fight against racism and discrimination, multiculturalism, immigration and urban development. The projections are also intended for others organisations, researchers, academics, students as well as any other person interested in the evolution of the ethnocultural diversity in Canada.

Subjects

• Immigration and ethnocultural diversity (formerly Ethnic diversity and immigration)
• Population and demography
• Population estimates and projections
• Visible minorities

Data sources and methodology

Target population

The target population for these projections is the entire Canadian population.

Instrument design

This methodology does not apply.

Sampling

This methodology does not apply.

Data sources

Data are extracted from administrative files and derived from other Statistics Canada surveys and/or other sources.

The base population for the projections is drawn from the database of the 2006 Census (20% microdata file), which was adjusted to take into account census net undercoverage.

The assumptions and parameters underlying the population projections were developed from various data sources: 1996, 2001 and 2006 population censuses (20% samples), surveys (General Social Survey, Ethnic Diversity Survey), and administrative data (population estimates, vital statistics, files of Citizenship and Immigration Canada, Longitudinal Administrative Database, 1991 Canadian census mortality follow-up database).

Error detection

This methodology type does not apply to this statistical program.

Imputation

This methodology type does not apply to this statistical program.

Estimation

The projections were established using a microsimulation model that differs from the traditional cohort component model in that it uses microdata rather than aggregated data, which allows to project a great number of individual characteristics.

The starting point for the projections consists of the microdatabase of the 2006 Census (20% sample), adjusted to take into account census net undercoverage. This database includes more than six million respondents, each with their individual characteristics: age, sex, marital status, place of residence, generation status and year of immigration, place of birth, visible minority group, mother tongue, etc.

As is also the case for the cohort-component model, the population at time T+1 results from changes undergone by the population in the previous year. But the changes occur at the individual level rather than at the level of population aggregates. In the model, an individual may change marital status, bear a child, change place of residence, leave Canada or die, among others. Also, new individuals are added over time, either through birth or through immigration.

For each person, the model calculates the probability that these events will occur based on the person's own characteristics. Thus, for example, the probability that a woman will give birth to a child differs depending on whether she is married or single, belongs to a visible minority group, etc. Using a Monte Carlo process and based on the probabilities associated with each event, the model determines for each individual which event will occur first and calculates the amount of time that will elapse before it occurs. Each time an event occurs, the probabilities are recalculated to take account of the individual's new characteristics. For example, the probability of changing one's place of residence declines after the birth of a child. The model advances individuals in this manner until 2031, unless they die or leave Canada in the meantime.

To operationalize such a model, it was necessary to use various data sources and methods (multivariate analysis, rates, transition matrices, etc.). The projection model also requires that assumptions be developed in advance on each of the components of population growth (including differential behaviours). Thus, this projection exercise is based on three fertility assumptions, three immigration levels, two ways of selecting immigrant characteristics, two assumptions regarding internal migration, and a single assumption regarding mortality and emigration. Five combinations of assumptions were then selected to create projection scenarios that are plausible in light of past trends.

Quality evaluation

Various mechanisms are used to ensure the quality of these population projections. First, at the beginning of each cycle, the data sources and methods used to produce the projections are reviewed in depth; an independent scientific committee is consulted in this regard. The choice of assumptions and scenarios is also examined through consultations with federal departments or the Advisory Committee on Demographic Statistics and Studies. Lastly, the projection results undergo detailed validation, including comparative analyses of the estimated and projected transitions and of past and projected trends for the populations of interest, as well as a comparison with other series of population projections.

Disclosure control

Statistics Canada is prohibited by law from releasing any information it collects that could identify any person, business, or organization, unless consent has been given by the respondent or as permitted by the Statistics Act. 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 order to prevent any data disclosure, confidentiality analysis is done using the Statistics Canada Generalized Disclosure Control System (G-Confid). G-Confid is used for primary suppression (direct disclosure) as well as for secondary suppression (residual disclosure). Direct disclosure occurs when the value in a tabulation cell is composed of or dominated by few enterprises while residual disclosure occurs when confidential information can be derived indirectly by piecing together information from different sources or data series.

Revisions and seasonal adjustment

The model may be subject to revisions to be carried out on a cost recovery basis.

Data accuracy

The accuracy of any projection depends on the quality of the data relating to the base population and the components of population growth, as well as the accuracy of the assumptions with regard to future trends. Projections are not predictions; rather, they represent an effort to establish plausible scenarios based on assumptions of population growth, which themselves are uncertain. As a result, it cannot be claimed that the values observed in the coming years will always remain within the range suggested by the low- and high- growth scenarios.