Errata: StatsCanada

"It is also a reminder that there is a human element to all statistics. Every major data series published by StatsCan [Statistics Canada] at some point has had something similar happen -- someone uses the wrong spreadsheet, forgets to check if all the responses are included, mindlessly inputs last month's data for this month, the list of possible mistakes is a census of human imperfection."
"There is even a seasonal component to these errors -- it is no coincidence that a similar event last August led StatsCan to delay its release of national household survey data. People are on vacation in summer, and those on duty are simply not as vigilant as in other months ..."
"The initial error may have been made by one person but, frankly, it should have been picked up. There were enough red flags out there. The system is built so there are checks and balances. I would say it's more of a collective failure of the checks and balances to pick this up."
"This isn't symptomatic of budget cuts, it's not symptomatic of the census. It's just somebody made a mistake."
Philip Cross, research co-ordinator, Macdonald-Laurier Institute, former chief economic analyst at Statistics Canada

"I struggle to think of a comparable foul-up anywhere in the world. The revisions are broad-sweeping and affected every major measure in a highly significant manner. Theories regarding how one single factor could be responsible for the revisions went straight out the window as StatsCan pointed to a systems error that affected everything."
Derek Holt, vice-president, Scotia-bank Economics

Canada Corrects Jobs Report for July

Canada's jobs numbers for July have been corrected to show that employment rose by 41,700, not the 200 that statistics agency first reported last week. The agency failed to count workers who should have been categorized as full-time employees.

According to corrected data, employment rose by 41,700 in July, the result of an increase in part-time work (+60,000). Full time employment declined by 18,100. 

The unemployment rate dropped 0.1 percentage points to 7.0%.

In the 12 months to July, employment increased by 157,000 or 0.9%, with most of the growth in part-time work. The total hours worked were up slightly (+0.3%) compared with July 2013.

When, earlier this month, Statistics Canada released its updated jobs figures with the published results of Canada having seen the creation of 200 new jobs in the last month it represented a stunning blow to expectations. One might think that the bright heads at StatsCan -- confronted with such an abysmally low figure for job creation when at least one hundred times that number was expected -- might reasonably have felt compelled to look again and yet again at the source of that conclusion.

Evidently not; the improbable number, dashing the hopes and anticipation of financial analysts and employment experts, was simply put out there for public view and consumption, and the country was beset with a headache and upset stomach over those results. On Friday the venerable numbers-crunching federal agency admitted that an "isolated incident" resulting from "human error" was responsible for the ridiculous numbers in its Labour Force Survey for July, released on August 8.

Now, the total loss of full-time employment stands at 18,000; dismal but much improved over the original 60,000 said to have been lost in the original report. The jump in part-time work remains unchanged from 60,000 and the unemployment rate remained at 7% for July, slightly improved over the previous month. "This was an isolated incident", Wayne Smith, the agency's chief statistician stated.

"I am fully confident in the integrity of the Labour Force Survey program", he emphasized, of the labour survey that undergoes a "major redesign", every decade. The last redesign at a cost of $5-million, had been launched in 2011 and it included an updating of the processing system used for the jobs report. "During the system change that was implemented with the July release, one program was not updated", admitted the agency.

"This was a human error that resulted in the incorrect processing of some data for July 2014 only. Certain respondents that should have been classified as employed were counted as not in the labour force, resulting in an over-estimation of job losses in full-time employment. The agency is confident in the accuracy of the corrected data. [An internal review was launched into] internal procedures ... to ensure that such errors are avoided in the future system updates to the Labour Force Survey, or any other program."

The newspapers were full of glee and blame over the awkward revelations that Statistics Canada, the branch of government at-a-remove that is so feted within Canada as the producer of reliably accurate statistics stumbled so badly. But, they claim, it isn't the agency's fault; clearly it is the fault of the Conservative-led government of Prime Minister Stephen Harper who has cut back departmental spending to such a degree that accuracy is imperilled. Those big, bad conservatives! If they weren't in power everything would be just fine.

And here again, is the former chief economic analyst at Statistics Canada: "First, the mistake was not due to a lack of resources. While there have been cutbacks at Statistics Canada recently, the agency knows not to cut the "Crown jewels" of its statistical program -- the labour force survey, the consumer price index and GDP. It is one thing to make an error in the estimate of livestock; just admitting to a mistake of unknown magnitude with the labour force survey is front page news ... While we are at it, let's discard the conspiracy theories about the government ordering up a better set of numbers than what was published Friday.
"No government would ever try something so ham-handed; all Statistics Canada would have to do is call a press conference and state that an attempt had been made to interfere with the data, and the government's credibility would be destroyed."