It looks like you're using an Ad Blocker.
Please white-list or disable AboveTopSecret.com in your ad-blocking tool.
Thank you.
Some features of ATS will be disabled while you continue to use an ad-blocker.
In the month leaded up to the election on November 8th, we repeatedly demonstrated how the mainstream media polls from the likes of ABC/Washington Post, CNN and Reuters repeatedly manipulated their poll samples to engineer their desired results, namely a large Hillary Clinton lead (see "New Podesta Email Exposes Playbook For Rigging Polls Through 'Oversamples'" and "ABC/Wapo Effectively Admit To Poll Tampering As Hillary's "Lead" Shrinks To 2-Points"). In fact, just 16 days prior to the election an ABC/Wapo poll showed a 12-point lead for Hillary, a result that obviously turned out to be embarrassingly wrong for the pollsters.
But, proving they still got it, ABC/Washington Post and CNN are out with a pair of polls on Trump's favorability this morning that sport some of the most egregious "oversamples" we've seen. The ABC/Wapo poll showed an 8-point sampling margin for Democrats with only 23% of the results taken from Republicans...
originally posted by: xuenchen
Here we go again with the fake polls.
originally posted by: butcherguy
a reply to: Greggers
Pretty damned accurate, except for the fact that most media outlets played everything up through election night that it take a miracle for Trump to win.
I remember seeing the Hillary lovers on ATS gloating about how Hillary had the election all sewed up.
Yeah, mostly accurate. They just got one thing wrong.
originally posted by: tothetenthpower
a reply to: Greggers
Nate Silver's polls were much better at finding the true election result. Although he still had Hillary winning, it was by a much smaller margin.
~Tenth
originally posted by: gortex
a reply to: xuenchen
"A total of 1,000 adults were interviewed by telephone
That is a very small poll.
originally posted by: Greggers
originally posted by: gortex
a reply to: xuenchen
"A total of 1,000 adults were interviewed by telephone
That is a very small poll.
You'd be surprised how large a population can be accurately estimated with a random sample of 1,000 people.
Here's a calculator where you can work it out for yourself.
originally posted by: corblimeyguvnor
Probability says you are wrong,
1000 sample size from a population of 600 million?
hope you don't capability studies for a living ..... perhaps i should put the data into Minitab and get some "P" value or other "Quality" statistics
originally posted by: Greggers
originally posted by: corblimeyguvnor
Probability says you are wrong,
No it doesn't.
1000 sample size from a population of 600 million?
The number of registered voters is about 146 million. If memory serves, a population of 146 million can be estimated with a random sample of just over 1,000 people with a 95% confidence level and a 5% margin of error.
hope you don't capability studies for a living ..... perhaps i should put the data into Minitab and get some "P" value or other "Quality" statistics
Or perhaps you should just stop talking out of your ass.