Highlights

View the most recent version.

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.

Archived

This page has been archived on the Web.

Sampling errors
Nonresponse
Coverage errors
Processing errors related to imputation

Sampling errors

• The coefficients of variation (CVs) of the estimates of average total expenditure per household for the provinces vary between 1.4% and 2.3%. The CV at the national level is 1.0%. The CVs are higher in the territories: 5.1% in Yukon, 7.6% in the Northwest Territories, and 6.0% in Nunavut.

• The coefficients of variation (CVs) of the average estimates for the different summary-level expenditure categories are in most cases less than or equal to 2.4% at the national level and generally less than 5.0% at the provincial level. The results for the dwelling and household equipment characteristics are similar. Since the sample size is smaller in Prince Edward Island and the territories, the CVs tend to be higher than the CVs of the other provinces.

Nonresponse

• The final response rate is 64.5%. The provincial/territorial response rates range from 59.6% in Ontario to 77.9% in Nunavut.

• The non-response rate is 35.5%. Nonresponse is due to refusals (21.7%), households that could not be contacted (10.8%), and households whose data were considered unusable (3.0%).

• The non-response rate tends to increase with the urbanization level. The non-response rate is 29.5% in rural areas and 38.3% in population centres with a population of 1 million or more.

• According to an analysis of non-response rates in strata consisting of the high-income geographic areas created under the sample design, the rate in high-income strata (40.9%) is higher than the rate observed in other strata (35.0%). The refusal rate for high-income strata (24.7%) is higher than the rate observed for other strata (21.5%).

Coverage errors

• Undercoverage of households is 12.2% at the national level.

• Undercoverage of persons is 16.1% at the national level (excluding the territories).

Processing errors related to imputation

a) Expenditure variables

• At least one expenditure variable¹ had to be imputed for 58.9% of households nationally. Contributing strongly to this rate is the section of the questionnaire dealing with expenditures related to residential communications services (telephone, cell phone and Internet access), cable television services, satellite distribution services and security services. For these services, respondent households have been allowed since 2004 to provide only the total expenditure for a package (bundled services), indicating which services are included. Approximately 45% of usable households required imputation for at least one of these six services.

• The overall imputation rate excluding these six services is 29.0% at the national level. At the provincial/territorial level, imputation rates vary from a low of 14.4% for Nunuvat to a high of 34.7% for Quebec.

• Imputed values account for 43.8% of the estimate of total expenditure on cable television services and 52.8% of the estimate of total expenditure on Internet access services. Imputation rates for households reporting expenditures on one or the other of these two services are respectively 44.5% and 58.5%. These higher rates are mainly due to the fact that among households that reported paying for a package, a large proportion of packages included these two services.

• About 10% of individuals required imputation of clothing variables, but in the vast majority of such cases, the respondents provided the totals and only the components were imputed.

• About 16% of individuals aged 15 and over required imputation of at least one variable in the Personal Taxes, Security and Money Gifts section.

b) Income variables

• Imputation of at least one income variable was required for 7.5% of individuals aged 15 and over.

c) Categorical variables

•  At least one categorical variable had to be imputed for 9.8% of households. Approximately 73% of them had only one variable imputed. At the provincial/territorial level, imputation rates range from a low of 4.3% for Newfoundland and Labrador to a high of 23.9% for the Northwest Territories. Categorical variables that required imputation can be found in the following sections of the questionnaire: Dwelling Characteristics; Facilities Associated with the Dwelling; Tenure; and Tobacco and Miscellaneous, for variables pertaining to purchases through direct sales.

---

Note

1. Excluding the Clothing section and the Personal Taxes, Security and Money Gifts section, which are collected at the individual level and not the household level.