The Commons: We talk in maths

By Aaron Wherry - Wednesday, May 8, 2013 at 6:24 PM - 0 Comments

And so it has been nearly three years since we, the previously vulnerable people of this vast land, were freed from the tyranny of the most-accurate data. Nearly three years since Tony Clement took a stand against all those interested in a particularly reliable basis for understanding the demographics of this country. Nearly three years since the Harper government vowed that Canadians should not be made to answer questions that no one seems to have been interested in asking.

And yet, oddly, with the release today of the results of the National Household Survey, that tribute to personal freedom and individual rights, Thomas Mulcair seemed rather uncelebratory.

“Mr. Speaker, today we have begun to see the consequences of the Conservatives’ backward decision to kill the mandatory long form census,” the NDP leader declared this afternoon. “Experts at StatsCan have confirmed that the data in the Conservatives’ new survey is deeply flawed. It contains contradictory information and 30% of Canadian families did not even bother filling it out. That is five times more than the last census.”

It seemed here that Mr. Mulcair had decided to hate freedom.

“The Prime Minister is not just satisfied to make public policy based on flawed information, that is his goal,” Mr. Mulcair ventured. “We have been calling on the Conservatives to reinstate the mandatory long form census for over three years. Will the Prime Minister finally listen?”

To listen, of course, is one thing. To heed is quite another. Continue…

Revisiting the census debate

By Aaron Wherry - Wednesday, May 8, 2013 at 1:20 PM - 0 Comments

In the process of arguing that we need to move on from the census, Philip Cross says the business community wasn’t much bothered by the elimination of the long-form census. He cites a few examples, but other groups were less unconcerned. The Canadian Federation of Independent Business had “grave concerns.” The CEO of the Toronto Board of Trade signed a letter expressing concern. And an internal survey of members of the Canadian Association of Business Economics found most opposed the change.

Jan Kestle and Vivek Goel, meanwhile, hope for a renewed debate.

We hope that Wednesday’s release of the NHS initiates a discussion about the importance of reliable national statistics. We recognize that the debates in the summer of 2010 may have been emotional at times. We trust that now, with knowledge of how the NHS has actually fared, we can have an informed discussion about whether it meets the collective needs of a large country and its communities.

But if the private sector can be left to fend for itself, as Cross seems to suggest, what of the public sector? The National Statistics Council released a proposal in 2010: keep the mandatory long form census, review the questions asked along strict criteria,  amend the Statistics Act to remove the threat of prison time and eliminate questions on household activities. Other international models were explored here, here and here.

What happened when the long-form census was replaced?

By Aaron Wherry - Wednesday, May 8, 2013 at 9:50 AM - 0 Comments

As was expected when the Harper government decided to scrap the long-form census and replace it with a voluntary survey, the new numbers arrive with some caveats.

Stephen Gordon explains the problem.

The National Household Survey findings on “immigration, place of birth, citizenship, ethnic origin, visible minorities, language and religion,” for instance, are here. Included is a note to readers.

The National Household Survey User Guide provides information on the methodology, collection, processing, evaluation and data quality of the National Household Survey (NHS).

Estimates and trends from other data sources suggest that certain population groups may be overestimated or underestimated in the NHS. Information on the quality of NHS data on immigration, place of birth, citizenship, ethnic origin, visible minorities, language and religion as well as explanations of concepts, classifications, questions and comparability with other data sources can be found in the series of reference guides for these topics.

Those reference guides include explanations of data quality. Here is the note on non-response bias for ethnic origin.

Non-response bias is a potential source of error for all surveys including the NHS. This issue arises when the characteristics of those who choose to participate in a survey are different than those who refuse. Statistics Canada adapted its collection and estimation procedures in order to mitigate, to the extent possible, the effect of non-response bias. (For more details please refer to the National Household Survey User Guide, Catalogue no. 99-001-X.)

Several data sources were used to evaluate the NHS estimates for ethnic origin such as: 2006 Census of Population, 2011 Census of Population results for mother tongue, the Longitudinal Immigrant Database (IMDB) and administrative data pertaining to permanent residents and non-permanent residents from Citizenship and Immigration Canada.

It is impossible to definitively determine how much the NHS may be affected by non-response bias. Furthermore, the reporting of ethnicity, and subsequent interpretation of the results, is complex, and poses challenges for comparisons with other data sources. There is evidence of non-response bias for other ethnocultural variables (e.g., Filipino population group could be overestimated in the NHS).

Generally, the risk of error increases for lower levels of geography and for smaller populations. At the same time, the data sources used to evaluate these results are also less reliable making it difficult to certify these smaller counts.

The reference for ethnic origin in the 2006 census is here.

Our complete archive of coverage of the long-form census controversy is here.

Census replacement to portray patterns of immigration, aboriginals and religion

By The Canadian Press - Tuesday, May 7, 2013 at 7:17 AM - 0 Comments

OTTAWA – Canada is about to find out how colourful a country it is. Just how vibrant the colours will be, however — well, that’s another story.

On Wednesday, Statistics Canada will publish the first part of its controversial National Household Survey, detailing patterns of immigration, Aboriginal Peoples, race and religion.

The first-of-its-kind voluntary survey, which compiles responses from more than three million people, replaces the cancelled long-form census. And even Statistics Canada itself has admitted it won’t match the detailed, neighbourhood-level information of its mandatory predecessor.

Continue…

Value of buildings permits up for third straight month in March: StatsCan

By The Canadian Press - Monday, May 6, 2013 at 9:55 AM - 0 Comments

OTTAWA – Statistics Canada says municipalities issued $6.5 billion worth of building permits in March, up 8.6 per cent from February.

The federal agency says March provided the third consecutive monthly advance, which came mostly from the non-residential sector in Ontario and Alberta.

The value of non-residential building permits rose 19 per cent to $2.8 billion, a second consecutive monthly gain.

Continue…

In wake of long-form census, Statcan braces for Wednesday release of survey data

By Jennifer Ditchburn - Sunday, May 5, 2013 at 3:24 PM - 0 Comments

OTTAWA – Has Statistics Canada — renowned around the world for its ability to take snapshots of Canadian life — lost some of its zoom?

The answer will come Wednesday, when the agency’s National Household Survey reveals how much critical information was lost in the controversial transition two years ago from a mandatory long-form census to a voluntary questionnaire.

Experts and observers say they expect the very specific, neighbourhood-by-neighbourhood information about certain types of Canadians — long a hallmark of the census — will be much more limited.

Continue…

Real GDP up 0.3 per cent in February, led by natural resources: StatsCan

By The Canadian Press - Tuesday, April 30, 2013 at 9:55 AM - 0 Comments

OTTAWA – The Canadian economy grew faster than expected in February, boosted by the resource industries and manufacturing.

Statistics Canada said Tuesday that the economy grew by 0.3 per cent in February, keeping pace with January which was revised upward to 0.3 per cent from 0.2 per cent.

Economists had expected February to come in at 0.2 per cent.

“February’s better-than-expected GDP growth on top of the upward revision to January means that growth in the first quarter is looking a fair bit better than we had expected,” TD Bank economist Leslie Preston wrote in a note.

“GDP growth is likely to be much closer to two per cent than the 1.6 per cent we had forecast.”

Continue…

Attacks on women fell between 2009 and 2011, but rate still higher than for men

By The Canadian Press - Monday, February 25, 2013 at 9:48 AM - 0 Comments

OTTAWA – Statistics Canada says police reports show that just over 173,600 women aged 15 and older were victims of violent crime in 2011, a rate of 1,207 victims for every 100,000 women in the population.

However, the agency says rates of police-reported physical assaults against women, including common assaults and serious physical assaults, fell five per cent to 705 victims per 100,000 women between 2009 and 2011.

The data also show a drop in rates of attempted murders against women over this same three-year period.

The agency says police reports show the rate of violent crime against women was about five per cent higher than the rate for men in 2011, although women were 11 times more likely than men to be a victim of sexual offences and three times more likely to be the victim of criminal harassment.

In 2011, police reported about 78,000 incidents of violence against women by current or previous intimate partners and the overall rate of intimate partner violence against women was 542 per 100,000 women, almost four times higher than the rate for men.

Common assaults accounted for about half of all police-reported violent crimes against women, followed by uttering threats (13 per cent) serious physical assaults (10 per cent), sexual assaults involving little to no physical injury (seven per cent) and criminal harassment or stalking, (seven per cent).

Busted furniture, smeared sheets: census-taker gave hotel rock-star treatment

By The Canadian Press - Tuesday, February 19, 2013 at 4:49 PM - 0 Comments

OTTAWA – Who knew census-takers could behave like rock stars?

Broken furniture. Stained carpets. Marker-smeared bed sheets and linens. Damaged wallpaper.

It may sound like something out of an old Led Zeppelin biography, but newly released documents show one enumerator’s wild romp left Statistics Canada with a hefty bill for a trashed hotel room.

The government first reported the payment last fall in its annual Public Accounts documents. But now there’s new photographic proof that census-takers know how to party.

Eight of them rolled into Brantford, Ont., in July 2011 and checked into the Hampton Inn and Suites. They were enumerators from the East Coast, conscripted to help with census work on the Six Nations reserve.

Continue…

Generation gap is wide when it comes to Internet use: StatsCan

By The Canadian Press - Wednesday, January 30, 2013 at 10:47 AM - 0 Comments

OTTAWA – Statistics Canada says people over 65 use the Internet more than they did a decade ago, but there’s still a wide generation gap when it comes to videos and music.

The agency says 60 per cent of seniors aged 65 to 74 and 29 per cent of those aged 75 and over had used the Internet in the month prior to the survey in 2010, while Internet use by the 15-25 age group was almost universal.

A decade earlier, Internet use at home was less than 10 per cent for people over 65.

Continue…

Richest one per cent earn a tenth of all income: StatsCan

By The Canadian Press - Monday, January 28, 2013 at 9:48 AM - 0 Comments

OTTAWA – Statistics Canada says the top one per cent of the country’s 25.5 million tax filers accounted for 10.6 per cent of the nation’s total income in 2010, down from a peak of 12.1 per cent in 2006.

However, that top one per cent also paid 21.2 per cent of all federal and provincial or territorial income taxes, down from the peak of 23.3 per cent in 2007.

In 2010, a tax filer required an annual income of $201,400 to be in the top one per cent, up from $147,500 in 1982.

Continue…

Canadians travelled less in October, but visits to Canada unchanged: StatsCan

By The Canadian Press - Tuesday, December 18, 2012 at 9:03 AM - 0 Comments

OTTAWA – Canadians took fewer trips abroad in October while the number of visitors to this country remained the same compared with September, according to a report from Statistics Canada.

The agency says Canadian residents took 5.4 million trips to the United States and overseas countries combined — a 1.9 per cent decrease from September.

Most of the October trips abroad — 4.6 million — were to the United States, a 2.1 per cent decrease from the month before.

Canadians also made fewer same-day car trips and overnight trips south of the border.

Statistics Canada also reports less overseas travel in October, with Canadians taking 805,000 trips — down 0.4 per cent from September’s record high of 808,000 trips.

Meanwhile, visitors from other countries made 2.1 million trips to Canada in October, which is the same as the month before.

The number of American visitors was down slightly, but trips made by people from other countries increased.

Statistics Canada says Americans took fewer same-day car trips and overnight plane trips, although they took slightly more overnight car trips.

Residents of countries other than the United States made 382,000 trips to Canada in October — a 2.6 increase from September.

Seven of the Top 12 overseas markets to Canada took more trips to Canada, with the United Kingdom remaining the top overseas marker, followed by France and Germany.

Travel from South Korea and China was up, while travel from Hong Kong was down.

‘Exercise caution’

By Aaron Wherry - Monday, October 29, 2012 at 9:46 AM - 0 Comments

This year’s census data comes with an asterisk.

The agency released its final tranche of the 2011 census last week, focusing on languages, but it included a big warning that cautions data users about comparing key facts against censuses of the past. “Data users are advised to exercise caution when evaluating trends related to mother tongue and home language that compare 2011 census data to those of previous censuses,” Statistics Canada states bluntly in a box included in its census material.

Those are strong words for a statistical agency, since they raise profound questions about how the data can be used reliably to come to conclusions about language trends. Officials have undertaken a thorough investigation, with a report to be published shortly. “There are a lot of questions and responses that don’t seem to add up,” said Doug Norris, the chief demographer for Environics Analytics and formerly a census manager at the agency.

Cancellation of long-form census taking toll on Statistics Canada data

By Heather Scoffield - Saturday, October 27, 2012 at 10:52 AM - 0 Comments

OTTAWA – Prime Minister Stephen Harper’s cancellation of the long-form census has started to take a toll on Statistics Canada’s data.

The agency released its final tranche of the 2011 census last week, focusing on languages, but it included a big warning that cautions data users about comparing key facts against censuses of the past.

Continue…

Job vacancies up in July compared to previous year

By The Canadian Press - Wednesday, October 17, 2012 at 9:55 AM - 0 Comments

OTTAWA – Statistics Canada says the number of job vacancies rose in July.

The agency says there were 264,000 vacant jobs in the month, up 32,000 from July 2011.

There were 5.3 unemployed people for every vacant job in July, down from 6.0 in the same month a year earlier.

The agency says the decline in the ratio of unemployment to job vacancies was mainly a result of an increase in vacancies.

The national job vacancy rate was 1.8 per cent in the three-month period ending in July, up from 1.6 per cent a year earlier.

The agency cautions, though that this is a new data series and trends are not yet available.

Thought you understood economy? StatsCan to send Canadians back to school

By Julian Beltrame, The Canadian Press - Sunday, September 30, 2012 at 10:21 AM - 0 Comments

OTTAWA – Statistics Canada is about to retell the country’s economic history for the past 30 years in a new move that will also provide more insight into murky economic concepts.

Starting Monday morning, the federal data agency will issue a comprehensive revision to economic data of the past 30 years, introducing new measures and changing the definition of others.

The exercise — two years in the making and designed to comply with revised international standards of economic measurements set out in 2008 — will put Canada in the forefront of nations, along with Australia, in adopting the new way of measuring economic performance.

Others have pledged to follow; the United States in 2013 and Europe in 2014.

It’s a big deal, say economists, but it won’t change the way Canadians feel about their economic place in the space at present, or in the past.

Some gross domestic product numbers will likely move marginally up, in part because research and development will be capitalized and some services will be added to the export tally.

But in broad terms, Statistics Canada is not rewriting the past — the new data will still dutifully record the slumps of the early 80s and 90s, the growth spurts that followed, and the great recession of 2008-09 and tepid recovery since.

“There’s no real change in the economic history of Canada,” says Jim Tebrake, Statistics Canada’s director of the income and expenditure accounts division.

“There are changes from quarter to quarter, but nothing of significance. The business cycle is still the business cycle.”

The value of the exercise, says Paul Jacobson, a Toronto-based consulting economist who has followed the process closely, is to give economic policy-makers and analysts a more precise picture of the ebb and flow of economic movements.

But it will take some getting used to. CIBC chief economist Avery Shenfeld has compared it to the transition from Fahrenheit to Celsius.

The comparison is somewhat apt because one of the benefits will be that countries, once they’ve followed suit, will more easily be able to stack their economies and component parts against each other.

But even economists will need some time to adjust, Jacobson says, adding that he has arranged for a four-hour seminar on the subject later in the month.

“I’ve been warning people for months this is going to be a biggie, but not everybody’s been paying attention.” he says. “Every single identifier people are using is changing, all the matrices change.”

He believes the exercise will be worth it. “It’s going to make things clearer about what the devil is going on.”

The new standards will be a bonanza for “data wonks,” Tebrake agrees. That’s because they will have so many more data points to follow.

For instance, total exports is currently broken down into seven groupings, now it will be 35. For personal expenditures, StatsCan will issue 100 sub-groupings for analysts to ponder, instead of the previous 38.

The business sector will be split between financial and non-financial corporations, and household income will become more precise after jettisoning tribal government activity, non-profit institutions, and other sectors that really had little relevance to households. Now they will have their own category.

“It’s a much purer and clear measure,” Teblake explains.

“I think at the end of the day it’s a more relevant product. Anyone who does forecasts has much better data at their disposal.”

The changes include re-definitions of categories and new terminology. For instance, terms such as corporate profits, labour income and personal expenditures will be no more.

One impact, say analysts, is that forecasters may need re-adjust their models to incorporate the new definitions, categories and adjusted GDP results.

But while Monday’s release by the agency is unlikely to impact the market or the Bank of Canada’s thinking about monetary policy, Shenfeld says there is a potential to alter some perceptions, if in the margins.

“If real GDP growth has been faster than we thought, Canada’s productivity performance hasn’t been as worrisome as feared,” he explains in a note issued to clients Friday.

At the same time, he said, changes in the definition of the household sector could result in Canadians realizing they are even more in debt on average than they thought, or maybe not.

In the end, he said, it will likely mean having “to get used to thinking in Celsius.”

Average payroll earnings rose in July: StatsCan

By The Canadian Press - Thursday, September 27, 2012 at 9:18 AM - 0 Comments

OTTAWA – Statistics Canada says the average weekly earning for non-farm payroll employees was $906.68 in July, up 1.1 per cent from the previous month.

It says the earnings were also up 4.1 per cent from July 2011, reflecting a number of factors, including wage growth, changes in the composition of employment, as well as average hours worked per week.

Five of the largest industrial sectors outperformed the national average: professional, scientific and technical services; educational services; accommodation and food services; manufacturing; and construction.

The biggest gain was in professional, scientific and technical services, where weekly earnings increased 6.1 per cent year-to-year, rising to $1,279.82.

Average weekly earnings for non-farm payroll employees increased in every province in the 12 months to July.

Growth was highest in Saskatchewan, Newfoundland and Labrador, Prince Edward Island and Alberta.

Retail sales rose 0.7 per cent in July, offsetting June decline

By The Canadian Press - Tuesday, September 25, 2012 at 8:49 AM - 0 Comments

OTTAWA – Statistics Canada says retail sales rose 0.7 per cent to $39 billion in July, more than offsetting a decline in June.

The results came in ahead of the 0.2 per cent that economists had been expecting.

The agency says eight of 11 subsectors accounting for 72 per cent of retail trade reported increases.

The increase was largely due to higher sales of cars, trucks and auto parts, as well as general merchandise. Automotive sales were up 1.7 per cent in July, mainly because of robust sales of new cars and high sales of recreational vehicles, motorcycles and boats.

General merchandise stores registered a 1.5 per cent increase with department store sales up 2.9 per cent.

Retail sales increased in all provinces in July.

Census replacement sees low response rates in 12 per cent of communities

By Heather Scoffield, The Canadian Press - Monday, September 24, 2012 at 4:43 PM - 0 Comments

OTTAWA – The response rate to Statistics Canada’s replacement for the cancelled long-form census varies wildly from community to community, information released Monday shows.

New data on the agency’s website about the contentious national household survey show that the final response rate across the country was 68.6 per cent — down slightly from an estimate made public earlier this month.

Continue…

Census: what Canadian couples look like

By macleans.ca - Wednesday, September 19, 2012 at 2:01 PM - 0 Comments

According to new census data from the Statistics Canada, the nation’s family structures are quickly changing.

The number of same-sex marriages nearly tripled between 2006 and 2011, and the number of same-sex common-law couples also rose by 42.4 per cent, the Canadian Press reports

Although the jump in same-sex marriage should come as no surprise—gay marriage was only officially legalized across Canada 2005—the rise in same-sex couples is more curious. The concentration of new same-sex couples in communities with higher rents, especially around the oil-patch, has some suggesting that some of the new couples were actually just roommates, and not romantically involved.

“We observed that there was a possible over estimation of same-sex families,” census manager Marc Hamel told The Canadian Press. “The counts for some smaller communities seemed too high.”

The number of heterosexual couples in common-law relationships also rose, they now make up 13.8 per cent of all couples. The Vancouver Sun reports that family with a step-parent rose to make up 1/8th of Canadian households, and more young Canadians are single. In 2011, 30.8 per cent of young adults in their 20s were in a couple, down from 32.8 per cent in 2006. In 1981, more than half (51.8 per cent) of young adults in their 20s were part of couples.

Other highlights from the Statistic Canada report:

• Married couples continue to be the most common family type, comprising 67 per cent of all census families.

• Continuing the new trend from 2006, there are more childless couples in Canada than couples with children.

• There are more male same-sex couples in Canada, but same-sex couples with children were overwhelmingly female.

• Same-sex couples are, on average, younger than heterosexual couples.

• 16.3 per cent of all families were lone-parent families.

• The number of young adults, age 20-29, living at home is no longer growing. It has leveled off and 40 per, the same as in 2006.

• Most twenty-somethings living at home they were male, single and under 24.

• 92 per cent of seniors (over 65) live in private households. The number of seniors living in nursing homes or retirement residences has remained stable, at roughly 7.9%, for a decade.

• Female seniors are twice as male seniors to live alone.

Define the Canadian family? It’ll require a flow chart

By Heather Scoffield, The Canadian Press - Tuesday, September 18, 2012 at 6:29 AM - 0 Comments

OTTAWA – To hear the politicians tell it, there’s a typical Canadian family out there that is the justification for many an election promise, tax break or new policy.

It’s a central theme of every party platform and speech. Last spring, Stephen Harper was “here for hard-working families,” the late Jack Layton offered “to give families a break” and Liberal hopeful Michael Ignatieff touted “your family, your future, your Canada.”

Continue…

Safer, but not safe

By Aaron Wherry - Monday, July 30, 2012 at 2:16 PM - 0 Comments

Conservative MP Guy Lauzon writes to his constituents about the latest crime statistics.

Last week Statistics Canada reported 2011 overall crime rates were down 6% over the previous year. This report is being welcomed as very good news. Any time crime rates are decreasing we should celebrate. However these statistics are only part of the story. Statistics also show that crime has increased 200% since 1962. This is a very alarming reality. We’ve gone from not locking our doors to needing state of the art security systems to protect ourselves and our possessions. Serious crimes like homicide and sexual offences against children are actually going up. For example child pornography went up an astounding 40%. That is why our Government recently passed the Safe Streets and Communities Act which increases penalties for sexual offences against children.

Some feel our Government is being too tough on crime. When we see statistics like those above, I don’t believe we are. By putting the bad guys in jail and keeping them there longer, we are preventing them from committing more crimes. We are stopping the revolving door of the criminal justice system. It appears our legislation is working. Undoubtedly there is much more to do, but a reduction of 6% in the overall crime rate is a step in the right direction. Our Government will continue to work to keep Canadian streets, communities and families safe.

Statistics Canada said that “fluctuations in the rate of child pornography are likely reflective of police-based programs and initiatives targeting this particular offence.”

Crime continues to decline

By Aaron Wherry - Tuesday, July 24, 2012 at 9:35 AM - 0 Comments

The murder rate increased slightly, but the overall crime rate and the violent crime rate declined in 2011.

Police reported over 424,400 incidents of violent crime in 2011, about 14,800 fewer than in 2010. As in previous years, violent crimes accounted for about 1 in 5 offences reported by police. Both the rate and severity of violent crime fell 4% in 2011. It was the fifth consecutive annual decline in the severity of violent crime. 

Despite the overall drop in violent crime, Canada’s homicide rate rose 7% in 2011 to 1.7 homicides per 100,000 population. Police reported 598 homicides in 2011, 44 more than in 2010. Despite annual fluctuations, the homicide rate has generally been declining since peaking in the mid-1970s. The national increase in homicides in 2011 was driven by increases in Alberta and Quebec. Manitoba had the highest homicide rate among the provinces for the fifth consecutive year.

The rate of robbery declined 3% in 2011, continuing a downward trend. Police reported over 29,700 robberies, 700 fewer than in 2010. Rates declined for attempted murder (-3%) and for most types of assault, including sexual assault (-3%).

The fiscal conservative case for statistics

By Aaron Wherry - Thursday, July 12, 2012 at 1:33 PM - 0 Comments

Lamenting for cuts at Statistics Canada, Vass Bednar and Mark Stabile suggest a fiscal conservative case for evidence-based policy.

These reductions have been masked under the compelling veil of “efficiency.” In reality, the cuts promise considerable future costs because they compromise the tools used to understand the state. This, in turn, has a high probability of leading to decisions that are no longer based on evidence, and therefore are likely to be ineffective uses of public money … Evidence-based policy-making requires just that — evidence — standard, reliable metrics whose quantification and legitimacy is widely agreed upon. In their absence, policy-making at all levels and in every sector will be as expensive as it is hopeful, while policy actors are forced to gingerly “guess and check” over time.