[web]https://www.ctv.ca/servlet/ArticleNews/s ... ?hub=World[/web]
-----
Shocking, really. Under 10,000?!?
Americans Underestimate Iraq Death Toll
Ridiculous that the article was even published in the first place and it was titled "Americans Underestimate Death Toll."The AP-Ipsos poll of 1,002 adults, conducted Feb. 12-15, had a 3 percentage point margin of error.
What a load of crap. 1002 adults polled out of a nation of 300 million. Pathetic "journalism" at its worst.
As far as I know, most opinion polls are carried out on around 1-2000 people - as long as the people who answered were from various demographic groups it would be fair.Kezza wrote:What a load of crap. 1002 adults polled out of a nation of 300 million. Ridiculous that the article was even published in the first place.The AP-Ipsos poll of 1,002 adults, conducted Feb. 12-15, had a 3 percentage point margin of error.
here's what wiki says:
https://en.wikipedia.org/wiki/Opinion_pollPotential for inaccuracy
[edit] Sampling error
All polls based on samples are subject to sampling error which reflects the effects of chance in the sampling process. The uncertainty is often expressed as a margin of error. The margin of error does not reflect other sources of error, such as measurement error. A poll with a random sample of 1,000 people has margin of sampling error of 3% for the estimated percentage of the whole population. A 3% margin of error means that 95% of the time the procedure used would give an estimate within 3% of the percentage to be estimated. The margin of error can be reduced by using a larger sample, however if a pollster wishes to reduce the margin of error to 1% they would need a sample of around 10,000 people. In practice pollsters need to balance the cost of a large sample against the reduction in sampling error and a sample size of around 500-1,000 is a typical compromise for political polls. (Note that to get 500 complete responses it may be necessary to make thousands of phone calls.)[1]
Whilst this may be standard practice for political pollsters, consider this: is it resposible to assess a 3% margin of error on a sample size of .000333 of the entire US population and then to title your findings in such a way that it represents the whole USofA?
I'm not arguing with the polling procedures (although these methods allow for much more inaccuracy than do those conducted for scienfitic purposes) but with the unfair language in which the findings were presented.
I'm not arguing with the polling procedures (although these methods allow for much more inaccuracy than do those conducted for scienfitic purposes) but with the unfair language in which the findings were presented.
-
major.tom
- Macho Business Donkey Wrestler
- Posts: 1970
- Joined: Sun Jan 21, 2007 7:07 pm
- Location: BC, Canada
Kezza] I didn't post this to be anti-USA. I posted it to show that a population is only as informed as their media allows them to be.
I too am skeptical (cynical, even) of polls, since the wording can skew the results whichever way desired. But even if the actual number is double or triple that from the poll (which would be very unusual given the margin of error) that still falls short of even Bush's pathetically low "guesstimate" (given so long ago, I don't even remember when he made it).
As Colbert put it at the 2006 White House Correspondents Dinner, "we didn't want to know and you [journalists] had the decency not to try to find out."
I too am skeptical (cynical, even) of polls, since the wording can skew the results whichever way desired. But even if the actual number is double or triple that from the poll (which would be very unusual given the margin of error) that still falls short of even Bush's pathetically low "guesstimate" (given so long ago, I don't even remember when he made it).
As Colbert put it at the 2006 White House Correspondents Dinner, "we didn't want to know and you [journalists] had the decency not to try to find out."
No worries, major.tom -- I didn't view your intentions to be anti-anything, and even if you are, it's your opinion and you're entitled to it.
And Colbert was brilliant at last year's Correspondents' Dinner -- so much so, that "the powers that be" are too full of chicken shit to invite him back. Instead, Rich Little will be this year's host. Who, you ask? Oh, yeah, that guy from the 1970's who does impressions and is viewed as a "safe" choice.
And Colbert was brilliant at last year's Correspondents' Dinner -- so much so, that "the powers that be" are too full of chicken shit to invite him back. Instead, Rich Little will be this year's host. Who, you ask? Oh, yeah, that guy from the 1970's who does impressions and is viewed as a "safe" choice.