For those who think that Stephen Harper detests academics, or is anti-science, particularly science of the social kind, or is waging a culture war, they were given new fodder at the end of June when it was announced that the long form census will no longer be mandatory. As Canadians have been reminded recently, the census consists of two main surveys. A short-form sent to all Canadians, and a longer form, sent to 20 per cent of the population that solicits detailed information about education, ethnicity, income, etc. In 2011 the short form will remain mandatory, while the longer form will be sent to more households to allegedly compensate for the fact that it is no longer a civic obligation, like paying taxes or participating in jury duty. The government is claiming that the long-form questionnaire is an unnecessary intrusion into Canadian’s private lives.
Canadian academics, at least those that have commented, have been unanimous in dismissing the idea as preposterously bonehead stupid. Because there will be some demographics that will be more likely to respond than others, census data will become skewed, rendering it almost useless. As professors and researchers rely on accurate information to do their jobs, and, because the government relies on accurate information (well, we hope anyway) to construct good public policy, injecting such a glaring sampling bias into the census (ie: the data from which all other data flows) will distort how Canadian society is understood.
“It’s not often that sample selection bias becomes an issue of national importance, but then again, it’s not often that census sampling design is outsourced to drunken monkeys,” Laval economist, Stephen Gordon wrote on his Worthwhile Canadian Initiative blog.
More diplomatically, the Canadian Association of University Teachers, which claims 65,000 members, wrote a letter to the prime minister urging that the long form census remain mandatory: “The long form Census is the only source of regular, highly detailed, systematic information on immigration, family and household structure, racialization, demography and other vital information about Canadians. While some information is available from other Statistics Canada surveys, for example on education, employment and income, the dramatically larger Census sample size allows vital detailed geographical breakdowns not otherwise available.”
The Canadian Economics Association wrote a similar letter: “Making this change without consultation will damage Statistics Canada’s currently outstanding reputation inside and outside of Canada and will leave Canada with a Census that is significantly less useful than those of the countries that Canada compares itself against.”
And from the Metropolis Centers of Excellence for Research on Immigration and Diversity: “Finally, by eliminating comparability with previous censuses, the proposed changes would significantly devalue ALL of the data collected in the long form of the census over the past half century.”
As for the question of privacy, Gordon argues that Statistics Canada is obsessively protective of information: “Anyone who has had dealings with Statistics Canada will tell you that they are ferociously – and at times irritatingly – determined to protect the privacy of those whose information is stored in their data bases. Researchers never see the data. They are obliged to send their estimation codes to StatsCan professionals, who run the programs and return the output to the researcher. That goes for all other non-StatsCan government employees as well.”
Aaron Wherry has a more complete list of organizations befuddled by the government’sdecision.