Munir Sheikh, the former chief statistician, explains the mess that is the National Household Survey.
The more important issue of replacing the census with the NHS is the potential for producing a downward spiral in the quality of social and household data over time … Statistics Canada collects a considerable amount of social and economic data using a range of surveys. These raw data are affected by response biases. Statistics Canada used to “adjust” these raw survey data by using the long-form census as an anchor. For example, if a population group’s survey response rate is low, Statistics Canada would use the group’s census weight to generate aggregate wage information.
A census used to be done every five years to ensure that the anchor provided appropriate, up-to-date information in order to adjust data from other surveys. We are now in a funny upside-down world: We’re using the old census data to fix the survey results when the objective was to find a new anchor to fix survey results because the old anchor was out of date.
I asked Statistics Canada for an accounting of the cost of the 2011 short-form census and NHS as compared to the short-form census and long-form census in 2006. Here is the explanation that was provided.
The total budget for 2006 Census was $567M and for the 2011 Census and NHS, it was $660M which included supplementary funding of $30M. Supplementary funding of $30 million was allocated to cover the costs associated with increased questionnaire production and mail-out for both the Census and the National Household Survey and increased field follow-up. $22 million of the supplementary funding was spent. Statistics Canada returned $8 million to Treasury Board, so $652 million was spent.
If you adjust for inflation, the amount spent in 2006 is equal to about $623 million in 2011. By that measure, the 2011 census and NHS cost $29 million more. If you’d rather use the acknowledged supplementary funding, the 2011 census and NHS cost $22 million more.
Either way, it would seem to have cost more money to produce less reliable data.