Sample composition/attrition

Archived Content

Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.

As mentioned, although originally designed as a longitudinal survey, one can also produce cross-sectional estimates from SLID data. Every non-longitudinal person living with a longitudinal respondent becomes part of the cross-sectional sample and is called a cohabitant. Table 2.1 and Table 2.2 show the composition of the SLID sample by province and by census metropolitan area (CMA) respectively, in terms of longitudinal sample persons who respond, longitudinal responding persons who are cross-sectionally ineligible (e.g. deceased or institutionalized persons and those who have moved outside of Canada) and responding cohabitants.

The cross-sectional SLID sample coverage is maintained through the addition of cohabitants each year. The one exception is immigrants who arrive after the beginning of a panel and before the start of the next one and move into their own households, this introduces a small amount of under coverage. The longitudinal sample, however, is subject to attrition. Attrition is the gradual loss of respondents each year through the life of the panel. Table 2.3 shows the respondent status for persons originally selected as longitudinal respondents. In Table 2.3 the responding longitudinal sample size is comprised of the in-scope respondents, the individuals who have moved to Yukon, North-West Territories or Nunavut, the individuals who have moved outside Canada, the institutionalized individuals and the deceased individuals.

Table 2.1 Sample composition of SLID persons by province, reference year 2006

Table 2.2 Sample composition in SLID by CMA, reference year 2006

Table 2.3 Status of longitudinal persons, reference year 2006