Statistics Canada
Symbol of the Government of Canada
Warning 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.

Data quality - Historical earnings and income data and outliers

Changes in methodology and response modes introduced in the 2006 Census resulted in improved income data. However, these changes also mean that some comparisons with data from previous censuses and some data for the highest earnings and income amounts are affected.

For the 2006 Census, changes to methods for capturing and processing the 2006 Census income data and the introduction of data from tax files may have an impact on the trends analysis for earnings at the individual level in particular (but also total income).

There are more reported small amounts in 2006 and less rounding of the amounts that now come from tax data. To compare from census to census, users are advised to consider full-year full-time earners as the presence of more small amounts tends to lower the mean and median when considering the full population of earners.

As in the past, when considering small populations, one or more outliers may affect the average. In regions with sampling, this makes the estimate of the mean unreliable because of the variance due to sampling for smaller populations. The standard error of the average should help identify these situations. With extremely small populations, the median might also be affected by the presence of outliers. Users are required to interpret data with caution when the sub-population has small or very small counts.