Return Of Long Form Census

guyser · February 5, 2015

Let me reprint this...

Almost every organization that deals with demographics disagrees with you.

Edited February 5, 2015 by Guyser2

On Guard for Thee · February 5, 2015

Where are the stats that show how many people filled out the long form truthfully when it was mandatory? If compliance is down you could be getting better data because people that volunteer are not likely to lie.

I have filled out a few of them in my days. Why would anyone be so stupid as to lie about such basic information.

Moonbox · February 5, 2015

Why? A census worker can still follow up and emphasize the importance of filling it out. The only thing that is gone is the legal club. Where is the evidence that this legal club is necessary? How many people were actually charged under the old law? I believe the answer is zero which makes it hard to believe the "civic duty" argument would not be effective.

I can't tell you how many people are charged with the old long form (it would be interesting if you have that data available), but I know that all sorts of people have been charged with refusing/failing to fill out the census in recent years. It's a $500 fine and up to 3 months in prison. Regardless, the threat of legal action (likely or not) is in many cases enough to influence behavior.

Every private company that uses stats for market surveys has to make do with voluntary participation. If it is good enough to make business decisions then it should be good enough for policy decisions. As I said: it is non issue that is being exploited a red meat for partisans.

The statistics from external surveys are notoriously unreliable and often next to useless. These companies can only dream about getting statistically representative sampling.

With a census there is no way to double check the answers and if someone is not motivated by the public good argument and needs the threat of jail time to motivate them then they have zero incentive to be honest.

There's no incentive to be dishonest about the census. The required effort for fudging your census responses is the same as filling it out truthfully. Lying on the census, therefore, serves absolutely no end and is counterproductive to good government and social policy. Spiteful census responses are about as intelligent and mature as a 4-yr old refusing to eat dinner to punish his parents. It's just being stupid, and I'd wager +95% of people fill it out properly. There'd be literally no reason not to.

Edited February 5, 2015 by Moonbox

jacee · February 5, 2015

Sorry but the country did not or will not fall apart because of it. So much drama.

We don't know the long term costs yet - eg, inappropriate allocation of funds.

.

jacee · February 5, 2015

Now decisions are being made on speculation rather than data.

I cannot believe that the same government which feels that the data collected is intrusive to individuals also supports little overview of CSIS - the most intrusive organization we have.

Best comments award!

.

TimG · February 5, 2015

There's no incentive to be dishonest about the census. The required effort for fudging your census responses is the same as filling it out truthfully.

I disagree. The long form census has many questions on things like the # of hours worked or the income earned. If someone does not have a full time work actually filling out the form correctly would take considerable effort to do the calculations. It is a lot easier to "make numbers up" or simply claim that no work was done. Also, one can omit household members to save time and the census people would be none the wiser. To get reliable data I think you need people filling out the form because they believe it is right thing to do.

But you are the one preaching the virtues of studies. Can you find any that examine the rate of dishonest answers on mandatory surveys? If not why do you *assume* that compelled data is necessarily better than volunteer data?

Note that in your link the problem noted was geographic resolution - i.e. not enough responses in a given area. That could be handled by increasing the number of long forms sent out. It is not an argument for mandatory forms.

Out of curiosity: do you believe that information gained from torture is reliable?

Edited February 5, 2015 by TimG

guyser · February 5, 2015

Out of curiosity: do you believe that information gained from torture is reliable?

The govt is well known (past and present) for going to homes and pointing a gun at the kids/pets/Grannies head to get the long form census completed.

:blink: :rolleyes: :blink:

On Guard for Thee · February 5, 2015

The govt is well known (past and present) for going to homes and pointing a gun at the kids/pets/Grannies head to get the long form census completed.

I think they do it nowadays by riding around in the Google car so they can get pictures of the take down as well.

Keepitsimple · February 5, 2015

Canada is one of the few remaining countries that still have a long-form census - if indeed there are any left at all. I'm not aware of any clamouring in other countries to collect more data. It's just more anti-Conservative puffery from the opposition and academia. Another tempest in a teapot.

TimG · February 5, 2015

The govt is well known (past and present) for going to homes and pointing a gun at the kids/pets/Grannies head to get the long form census completed.

Typical. Ignore the point. The point is torture is the extreme example of using force to get information and it is not particularly reliable. And that begs the question: if torture is not reliable then why are lesser forms of compulsion considered to be any more reliable? In the end, the data can only be good if people believe that there is a benefit to providing it. Threatening fines only ensures that the boxes on the forms are checked off. It does not ensure that the answers have any connection to reality.

On Guard for Thee · February 5, 2015

Typical. Ignore the point. The point is torture is the extreme example of using force to get information and it is not particularly reliable. And that begs the question: if torture is not reliable then why are lesser forms of compulsion considered to be any more reliable? In the end, the data can only be good if people believe that there is a benefit to providing it. Threatening fines only ensures that the boxes on the forms are checked off. It does not ensure that the answers have any connection to reality.

I think most people quite readily understand the value of providing the info. They just happen to fill in the info at a much higher rate when it was compulsory. Thus the info was much more reliable.

guyser · February 5, 2015

Typical. Ignore the point.

Not ignore, I mocked it because it was a dumb point trying to be made.

The point is torture is the extreme example of using force to get information and it is not particularly reliable. And that begs the question:

The question is madatory long form census is not torture....in any way shape or form.

In the end, the data can only be good if people believe that there is a benefit to providing it. Threatening fines only ensures that the boxes on the forms are checked off. It does not ensure that the answers have any connection to reality.

Like taxes.

Moonlight Graham · February 5, 2015

If the opposition actually cared about the quality of data they would be educating the public about the importance of choosing to fill it out. But they would rather use it as red meat to rile up their base.
I personally cannot see why any statistician would put more weight on data that was gathered under threat than data that was volunteered. i.e. if I did not want to fill out a census form but was compelled to I would lie and my data would then be useless to the people collecting.

Good points.

guyser · February 5, 2015

It's just more anti-Conservative puffery from the opposition and academia. Another tempest in a teapot.

Heaven forbid that actuarial folk,scientists,researchers, academia are all performing puffery .

Lets face it, the savings werent there for the value given up . This is just a govt who wants to form their own data to do what they want to do.

Transparent to all but those who bleed blue.

TimG · February 5, 2015

I think most people quite readily understand the value of providing the info. They just happen to fill in the info at a much higher rate when it was compulsory. Thus the info was much more reliable.

Then where are the studies to support your assumption? The only information I have seen is a naive assumption that if the forms are filled out they must have good data. This is a not a reasonable assumption to make. Edited February 5, 2015 by TimG

Black Dog · February 5, 2015

Let me reprint this...

Almost every organization that deals with demographics disagrees with you.

Tim only listens to expert when he supports their conclusions.

Then where are the studies to support your assumption? The only information I have seen is a naive assumption that if the forms are filled out they must have good data. This is a not a reasonable assumption to make.

Where's the evidence that false data was an issue at all?

TimG · February 5, 2015

Like taxes.

The only thing that keeps people honest on taxes is the threat of an audit where their tax return is compared to other data and any discrepancy must be explained. There is no threat of a audit for census data - as long as the boxes are checked off you are free and clear even if your answers are complete fiction.

TimG · February 5, 2015

Where's the evidence that false data was an issue at all?

The people out there moaning about the need for a mandatory census have the duty to show that mandatory census actually provides a benefit. This also means they have to show that compelling people to fill out forms does not result in a rate of false answers that undermines the value of the data. Simply assuming that the data is good is not enough to justify a law. Edited February 5, 2015 by TimG

Black Dog · February 5, 2015

The people out there moaning about the need for a mandatory census have the duty to show that mandatory census actually provides a benefit.

Why, so you can dismiss them with baseless nitpicking?

This also means they have to show that compelling people to fill out forms does not result in a rate of false answers that undermines the value of the data. Simply assuming that the data is good is not enough to justify a law.

Simply assuming the prevalence of false data doesn't justify scrapping it either. Not even the HarperCons went down that road.

guyser · February 5, 2015

The people out there moaning about the need for a mandatory census have the duty to show that mandatory census actually provides a benefit.

How many do you want?

There arent any actuaries,scientists,researchers, academia and so on who think not having this data is good for anyone....except those who wish to govern by ....oh whatever bullshit reason they come up with.

Hell, the party of Crack down on Crime bozos never did read Stats Can numbers about falling crime rates. They just appeal to that ignorant base that 'thinks' crime is up.

Moonbox · February 5, 2015

I disagree. The long form census has many questions on things like the # of hours worked or the income earned. If someone does not have a full time work actually filling out the form correctly would take considerable effort to do the calculations. It is a lot easier to "make numbers up" or simply claim that no work was done.

I don't think the census makes any expectation that people are going to accurately calculate their income and work days down to the dollar/hour. A best guess is usually good enough. The census isn't a tax return.

Also, one can omit household members to save time and the census people would be none the wiser. To get reliable data I think you need people filling out the form because they believe it is right thing to do.

The amount of time saved is negligible. If you're already making a point of filling it out, you might as well take the extra couple of minutes to fill it out properly.

But you are the one preaching the virtues of studies. Can you find any that examine the rate of dishonest answers on mandatory surveys? If not why do you *assume* that compelled data is necessarily better than volunteer data?

It's common sense Tim. People generally lie for a reason. If it doesn't get you anywhere, why would you bother? Are you that spiteful?

Note that in your link the problem noted was geographic resolution - i.e. not enough responses in a given area. That could be handled by increasing the number of long forms sent out. It is not an argument for mandatory forms.

Out of curiosity: do you believe that information gained from torture is reliable?

Yes, under the right circumstances. What are you getting at?

TimG · February 5, 2015

Why, so you can dismiss them with baseless nitpicking?

Because the only argument in favor I have seen simply assumes, without evidence, that the data is good.

Simply assuming the prevalence of false data doesn't justify

scrapping it either.

No law should be imposed with sufficient justification. The conservative argument is the benefits from making the census mandatory are not large enough to justify a law. The opposition is now whining about how "bad" the data is from the voluntary census but the only difference I can see is in a lower rate of response which just means more long forms need to be sent out.

Black Dog · February 5, 2015

Because the only argument in favor I have seen simply assumes, without evidence, that the data is good.

I've seen no evidence the data is bad, so it's unclear why your unsupported belief should carry the day. Though I suspect people who actually use this data have a sense of how reliable it is, but what do the experts know?

No law should be imposed with sufficient justification. The conservative argument is the benefits from making the census mandatory are not large enough to justify a law. The opposition is now whining about how "bad" the data is from the voluntary census but the only difference I can see is in a lower rate of response which just means more long forms need to be sent out.

Ah yes, the classic conservative approach of spending more money to get the same results (but without getting the same results).

Bonam · February 5, 2015

Seems to me like the government should just ask Google/Facebook/etc for some data, and they will know 100x more about people than just having a census, however long or mandatory. In fact, the government already does this anyway, it's just that CSIS needs to share that data with Statscan. Additional advantages include data that is up to date within several days, rather than a single survey once every several years.

Edited February 5, 2015 by Bonam

Keepitsimple · February 5, 2015

Heaven forbid that actuarial folk,scientists,researchers, academia are all performing puffery .

Lets face it, the savings werent there for the value given up . This is just a govt who wants to form their own data to do what they want to do.

Transparent to all but those who bleed blue.

Like I said - almost all countries have stopped collecting this kind of data. They limit their census to population and housing because other granular data is available through other sources or individual surveys. We're one of the last holdouts and we still do an excellent job in providing a lot of free data. Tempest in a teapot. Funny how the Left wants us to copy other countries when it suits their issue but whines that "we're not like other countries" when it doesn't.