Data quality, concepts and methodology: Survey methodology

View the most recent version.

The survey universe

The 2007 Survey of Household Spending was carried out in private households in Canada’s 10 provinces. ¹ 

The following groups were excluded from the survey:

1. those living on Indian reserves and crown lands (with the exception of the territories);
2. official representatives of foreign countries living in Canada and their families;
3. members of religious and other communal colonies;
4. members of the Canadian Forces living in military camps; and
5. persons living full time in institutions: for example, inmates of penal institutions and chronic care patients living in hospitals and nursing homes.

The survey covers about 98% of the population in the 10 provinces and three territories.

Similar to the 2006 survey, spending data were collected for every household member at the time of the interview, including those who joined the household in 2007 and 2008 regardless of whether the previous household existed or the person was living alone. Data were not collected for those who left the household in 2007 or 2008.

As a result, an important difference between the 2006-2007 SHS and previous SHS methodology is the elimination of the distinction between “part-year” and “full-year” members and households.

Persons temporarily living away from their families (for example, students at university) were included in the household to avoid double counting.

Survey content and reference period

Detailed information was collected about household expenditures for consumer goods and services, changes in assets, mortgages and other loans, and annual income. This information was collected for the calendar year 2007 (the survey reference year).

Information was also collected about dwelling characteristics (e.g., type, age and tenure of the dwelling) and household equipment (e.g. appliances, communications equipment, etc.). The reference date for this information was the time of the interview.

Because the Survey of Household Spending is designed principally to provide detailed information on non-food expenditures, only an overall estimate of food expenditure is recorded. Detailed information on food expenditure is provided by the Food Expenditure Survey which was last conducted in 2001. In February 2003, the results were published in Food Expenditure in Canada, 2001, Catalogue no. 62-554-X.

The sample

The sample size for the 2007 Survey of Household Spending was 21,407 eligible households.

The SHS sample was a stratified, multi-stage sample selected from the Labour Force Survey (LFS) sampling frame.Sample selection comprised two main steps:the selection of clusters (small geographic areas) from the LFS frame and the selection of dwellings within these selected clusters. The current LFSsampling frame is based on 2001 Census geography and 2001 Census population counts. ² 

Data collection

The 2007 Survey of Household Spending was conducted from January to March 2008. Data were collected by computer assisted personal interview (CAPI) using a lap-top personal computer. A copy of this questionnaire is available on the Statistics Canada website.

Data processing and quality control

Due to introduction of the new electronic CAPI questionnaire, changes were made to the data processing and quality control steps.

Similar to the 2006 Survey of Household Spending for 2007 SHS, the interviewers recorded the information provided by the respondents using a laptop and performed the initial editing at the same time. For example, the range edit provided a minimum and maximum amount for certain purchases and was triggered if the amount entered by the interviewer was unusual. Other edits indicated inconsistencies in responses, e.g. if the household tenure was “renter” but no rent was paid. In addition to automatic edits built into the electronic questionnaire, a balance edit comparing total revenues, expenses and changes in assets and liabilities performed by the interviewer acted as a check on data quality.

The next stage of editing was done in the head office to verify unusual or high values and inconsistencies, and to correct invalid responses.

If a household indicated that it had an expense but could not provide the amount, these missing responses were imputed using the nearest neighbour method. Statistics Canada’s Canadian Census Edit and Imputation System (CANCEIS) were used to insert values from donor records having similar characteristics, chosen specifically to fit the variable. For example, total household income was used for most variables; dwelling type, household size and province were also frequently used.

Tabulation of the 2007 Survey of Household Spending results was completed using a PC/client server-based system. This system provides tools (database querying, searching, and viewing capabilities) for spotting systematic errors.

Next