Data quality, concepts and methodology: Weighting, re-weighting, and Census historical revision of Survey of Household Spending

View the most recent version.

Users should note that the estimates for the SHS reference years 1997 to 2003 have been revised. These revisions were published along with the 2005 survey results in December 2006.

The estimation of population characteristics from a sample survey is based on the idea that each sampled household represents a certain number of other households in addition to itself. These numbers are called the survey weights of the sample. To improve the representativity of the sample, the weights are adjusted so that the estimates from the sample are in line with population totals, or benchmarks, from other independent sources of information that are considered reliable. This is called weight calibration.

SHS uses two sources for calibration. The first source is the Census of Population which provides demographic benchmarks. From 1997 to 2003, SHS used benchmarks derived from the 1996 Census. Beginning with the 2004 reference year, the SHS uses survey weights which take into account new population projections from the 2001 Census. In order to make these estimates comparable over time, the weights for all previous SHS have been revised using the new 2001 Census data.

The second source used for adjusting the survey weights for SHS are T4 data from the Canada Revenue Agency, which ensures that the estimated distribution of earners in the survey matches the one in the Canadian population.

The current calibration strategy is as follows:

1. Age
   At the provincial level there are controls for 8 age groups (0-6, 7-17, 18-24, 25-34, 35-44, 45-54, 55-64, 65+).
   At the CMA level: two age groups (0-17, 18+).
2. There are controls for three size of household categories (one person, two persons, 3+).
3. T4 adjustments are made to the weights of the population for income from wages and salaries (0-25^th percentile, 25^th-50^th, 50^th-65^th, 65^th-75^th, 75^th-95^th, 95^th-100^th).

Due to their smaller population, only two age groups are used for the three northern territories: number of persons under 18 and number of persons 18 and older. The weights are also calibrated to the totals for one-person households, two-person households and households with three or more persons. Before the historical re-weighting the calibration strategy varied slightly between the territories and between survey years. The northern calibration is now consistent across all three territories and over time.

The weights and calibration strategy were implemented for SHS for the years 1997 and onward resulting in revised estimates of household spending for each year up to 2003. Users of SHS data should take care to make comparisons using the re-weighted data.

Next | Previous