Survey of Household Spending 2009: Data Quality Indicators

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This page has been archived on the Web.

Introduction

The Survey of Household Spending (SHS) is an annual survey that collects data on household income and expenditure using personal interviews. The 2009 SHS sample consists of 16,758 households¹ distributed throughout the ten provinces and three territories.  This is a decrease of about 25% in the usual SHS sample size (before 2008), and as a result, the estimates will have higher coefficients of variation. Collection takes place in January, February and March, and income and spending figures are obtained for the period from January 1 to December 31 of the previous year. Following a redesign that took place in 1997, this survey replaces the periodic Family Expenditure Survey and the Household Facilities and Equipment Survey (with modifications to questionnaires and samples).

Like all surveys, the SHS is subject to errors, despite all the precautions taken at the various stages of the survey to control them. While there is no comprehensive measure of the quality of the data generated by a survey, some quality measures produced at the different stages of the survey can provide users with the information they need to interpret the data properly.

This report describes the quality indicators produced for the 2009 Survey of Household Spending. It covers the usual quality indicators that generally help users interpret data, such as coefficients of variation, response and non-response rates, slippage rates and imputation rates.

The quality indicators are grouped by the main types of error in a survey. Section 1 deals with sampling errors—that is, errors due to the fact that the inferences about the population drawn from the survey are based on information collected from a sample of the population, rather than the entire population. The remaining sections cover non-sampling errors. Nonresponse and coverage errors are discussed in sections 2 and 3. Response errors and processing errors are dealt with in sections 4 and 5 respectively.

This report focuses on data quality. For a detailed description of the methodology of the survey, see reference [1].

---

Note

1. The initial sample is made up of 20,146 dwellings. Ineligible dwellings are then identified and removed (see section 2.1), leaving the 16,758 households from which data on expenditure and income are collected.