Four links on the Canadian census

Tonight, I thought I'd limit myself to posting four links dealing with the transformation of the Canadian census from a detailed mandatory form to a shorter optional questionnaire. (I've blogged about the issue here on several occasions, link to these post to be found here.)

The Toronto-focused blog Torontoist's Max Hartshorn asked in "Can An Optional Questionnaire Fill the Shoes of the Long-Form Census?" the question of the post's title. Given the likelihood of over- or under-representation of different demographics, the likelihood that recent trends may be missed, and the generallly lower resolution of the National Household Survey, the answer seems to be a decided "no."

The major problem with an optional survey, Hiu says, is that it may over- or under-represent certain segments of the population. When you give a group of people an optional questionnaire, there is always a chance that those who don’t respond will differ in meaningful ways from those who do. In the case of the NHS, researchers argue that ethnic minorities, and individuals with very low or very high incomes, will be least likely to respond.

[. . .]

One possible solution is to use data from previous censuses to fill gaps in NHS results. The so-called "imputation" of missing results through the aid of external data is a standard statistical technique. But it runs into problems if the data you are using to plug holes differ in meaningful ways from your obtained results.

[. . .]

Such technical issues are of great concern to Toronto city planner Tom Ostler and health policy professional Paul Fleiszer, both of whom use the long-form frequently in their work.

Fleiszer, who works for Toronto Public Health, says that his department “uses data on language, immigration, ethnicity, income, and education, all previously available from the long-form, to guide our programs and policies."

"For example, we offer tuberculosis prevention initiatives to people that have immigrated from countries where tuberculosis is endemic. The long-form identified areas where those populations live so we knew which neighborhoods to offer classes in."

"One critical [item] that we use in city planning in particular," Tom Ostler says, "is the question of where people work and linking that question to where they live. [This gives us] a picture of commuting flows across the city," which can help in planning bus routes and transit initiatives.

"Even just a basic statistic like the number of people who are working inside the city of Toronto," Ostler explains, helps the City set job targets for the future. These targets influence how much money will be invested in employment services and infrastructure.

"At the end of the day," says Fleiszer, "if you don't have good data, you can't make good decisions. That irritates me as a public health professional."

At The Search, Douglas Todd observed that the census, by providing a finely-detailed portrait of the Canadian population in all of its diversity, allows government to respond and treat the different issues of these populations accordingly. It's a long-standing tradition, after all.

According to senior Statistics Canada official Tina Chui, the federal government has been asking about religion and ethnic origin since 1871.

Even though some countries don't include such questions in their census, Ottawa originally asked them because the country's two "founding" peoples were French (mostly Roman Catholic) and British (mostly Protestant).

It wouldn't have been possible more than a century ago for the federal government to respond fairly to the contrasting needs of these two ethnic/religious groups if it didn't have facts and figures about them.

Now that multicultural Canada, which has the world's highest immigration rate per capita, is home to people who speak more than 200 languages, it's more important than ever to track residents' ethnicities and religions.

[. . . T]his year's census questions have been translated into more than 30 languages, including Chinese, Arabic, Hindi, Creole, Romanian and many aboriginal tongues. Moreover, census staff are always following up to encourage completion.

Why go to all the trouble? Chiu reminds us that solid ethnic and religious data will help school boards serve diverse students. They will aid ethnic community groups in supporting their clients. They will assist businesses in targeting customers, based on cultural backgrounds. They will lend a hand to researchers monitoring ethnic and religious discrimination, and governments creating effective training programs.

The CBC posted a simple article: "Census workers getting partial answers on householder surveys".

Statistics Canada is accepting incomplete forms – called partial responses – and there is no followup.

"On the (short) census, we will follow up since the census is mandatory, so if we don't have a minimum amount of information or there are inconsistencies, it is possible that we'll call people to clarify the information that was provided," said Marc Hamel, director general of the census management office.

"We don't do that on the National Household Survey. We make the assumption ... if they have omitted to complete one question or a section, we go on the assumption knowing that it's a voluntary survey that they've omitted to complete that on purpose."

One census enumerator, who spoke to The Canadian Press on condition of anonymity, said workers had been instructed to accept the long forms with as few as 10 of 84 questions answered. They can also declare somebody has given them a "total refusal" simply by speaking to them on the phone.

"We can try and convince them and talk about how it's a good thing, but a lot of people shut down the conversation quickly when they find out it's not mandatory."

Finally, the Globe and Mail's Stephen Gordon is very unhappy with what is happening.

As Economy Lab contributor Kevin Milligan and his UBC colleague David Green note in Canadian Public Policy, one of the most striking features of the census is its ‘hidden ubiquity’. The census is an invisible -- and yet essential -- element of virtually all the data that inform policy debates.

The Labour Force Survey (LFS) is the source of the monthly employment data release. Some 55,000 people are polled, and participation is (so far) mandatory. But in order to make sure that this panel of 55,000 people is a representative sample, the LFS checks to see if its panel has the same features as the Canadian population as a whole: levels of income, education and the like. The only available reference point to make this verification is the census. As time passes, it will be less and less clear if announced changes in unemployment rates are due to what is actually happening in the labour market, or is simply an artefact of an increasingly biased sample.

The Consumer Price Index (CPI) tracks the price of a ‘representative basket’ of goods and services. The price of this basket is of interest only insofar as it is representative of Canadians’ expenditures, and estimates for representative spending patterns are based on the Survey of Household Spending. This is a voluntary survey, so responses have to be corrected so that the panel or respondents reflects the general population. Again, the only available reference for making this correction is the census.

Employment and inflation data have the power to move markets, and policy-makers need reliable data to guide their decisions. The list is goes on, and is almost endless. For example, the labour market experiences of immigrants will be an increasing preoccupation for policy-makers as the population ages; the only source of information about immigrants is the census.

Go, read all these sources.