Don’t compare household survey numbers to long-form census, Toronto tells city staff

TORONTO – The city is cautioning its staff not to compare National Household Survey information with data from the long-form census.

“Because of the change from a mandatory to a voluntary sample, the NHS may under-report the number of people belonging to certain subgroups,” reads a briefing note being sent out to key staff members who would normally work closely with this kind of demographic information.

“Comparisons between the 2011 NHS numbers and 2006 (and earlier) Census numbers may not be accurate and should not be made,” the note continues, “until Statistics Canada’s methodology and documentation has been reviewed.”

The household survey, some of whose results were released Wednesday, is meant to replace the long-form census, which the federal government scrapped in 2010. Because the survey is voluntary its numbers are less reliable than mandatory census data.

Its numbers are also more expensive: Statistics Canada is now charging for more detailed neighbourhood-level information, which was previously free.

The City of Toronto, like government agencies, researchers, businesses and non-profits across Canada, relies heavily on the census’ demographic data to inform everything from transit planning to business expansion to outreach programs.

Paul Fleiszer, manager of surveillance and epidemiology at Toronto Public Health, is leery about using the information at all – especially in his department: “In terms of public health practice, where greater precision is required, greater caution should be exercised.”