Census response rate is 98 per cent, early calculations show

TheGlobeAndMail.com
July 21, 2016
Tavia Grant

Canadians really were, it seems, enthusiastic about the census.

Statistics Canada is still calculating exact response rates, but it says early indications are that the overall response rate is 98 per cent – and about 96 per cent for the long-form census. That is higher than long-form response rates in the previous two censuses, the agency says.

“Early indications are positive,” Marc Hamel, director-general of the census program, said in an interview.

These numbers could shift up or down as results from early enumeration of Northern communities, late filers and First Nations reserves are added in, he said. “The range of error is not very high … it’s likely to move, but we’re talking most likely, at most, one percentage point.”

The census, conducted every five years, is a massive undertaking. The budget for the current census is $715.2-million and involves the temporary hiring of more than 35,000 people.

The sample size for the long-form census was increased to one in four households this year from one in five in 2006. The combination of high response rates this year and a bigger sample size will yield “incredibly precise data,” chief statistician Wayne Smith said.

He called this “probably the most successful census since 1666,” the year of the first census in what became Canada – when 3,215 inhabitants (of European background) were enumerated.

Still, there have been wrinkles – among them, Fort McMurray, Alta. The census was suspended there in May after a wildfire caused a citywide evacuation. As a result, Statscan may use administrative data (such as tax and migration records) to calculate a population count, and is still determining whether there’s time to have residents complete the long-form census so that their responses will be included in the census’s main database.

The goal is to have a portrait of the city as it was on May 1 – just before the wildfire, Mr. Hamel said.

There have been other challenges. He said some people had privacy concerns about filling out the forms online. A help line fielded more than one million calls from the public on questions such as how information will be protected.

Statscan produces two sets of response rates for the census – the initial collection rate (which should be officially tallied by September) and the final response rate, which is slightly lower as forms with too few answers are discounted. In 2006, Statscan did not produce a long-form collection response rate. But it says the final 2006 response rate was 93.8 per cent, while in 2011, when the long form was changed to a voluntary household survey, the rate was 68.6 per cent.

“From experience, the difference between the collection and final rate has always been less than one percentage point,” Statscan said. “Given this, it is safe to conclude that the 2016 rate for the long form, although not final yet, will surpass the rate for 2006.”

Completion rates on the long form this year are the same or higher than in 2006, the agency said. About 67 per cent of people responded online this year, a record.

This year’s effort has not been without criticism. Some people have felt harassed by repeated calls from census staff, even after completing their questionnaires, according to media reports. And some seniors who live in collective housing, such as retirement homes, were angry at being excluded from getting forms, the Ottawa Citizen reported.

At last count, 13.74 million questionnaires had been completed out of a total of about 14 million households. (Statscan had initially sent the census to about 15.7 million dwellings, but not all are occupied or still exist as homes, so the total has gone down). “We’re adjusting both the numerator and the denominator every day, so this is why this number is changing,” Mr. Hamel said.

The last census was the subject of controversy after the former federal Conservative government axed the mandatory long-form census in favour of a voluntary household survey. Many researchers said the switch resulted in poorer-quality data. One consequence of the public debate may be that it raised awareness about the importance of the census, which could have bolstered response rates.

It’s still early to declare whether this year’s response rate is higher, but it is likely in the ballpark of 2006, which is surprising to Doug Norris, chief demographer at Environics Analytics. “All of the discussion about the cancellation and reinstatement of the long form certainly generated a lot of media about the census – people were much more aware,“ he said, adding that Internet access may also have helped 2016 response rates.