Sam how were the polls biased? According to the definition of statistical bias
A statistic <http://en.wikipedia.org/wiki/Statistic> is *biased* if it is calculated in such a way that is systematically different from the population parameter <http://en.wikipedia.org/wiki/Statistical_parameter> of interest. http://en.wikipedia.org/wiki/Bias_(statistics) A bias sample is a bias <http://en.wikipedia.org/wiki/Bias> in which a sample is collected in such a way that some members of the intended population <http://en.wikipedia.org/wiki/Statistical_population> are less likely to be included than others. It results in a*biased sample*, a non-random sample <http://en.wikipedia.org/wiki/Random_sample>[1]<http://en.wikipedia.org/wiki/Biased_sample#cite_note-1> of a population <http://en.wikipedia.org/wiki/Statistical_population> (or non-human factors) in which all individuals, or instances, were not equally likely to have been selected.[2]<http://en.wikipedia.org/wiki/Biased_sample#cite_note-2> If this is not accounted for, results can be erroneously attributed to the phenomenon under study rather than to the method of sampling<http://en.wikipedia.org/wiki/Sampling_(statistics)> . http://en.wikipedia.org/wiki/Biased_sample >From what I've seen and others have also pointed out the proportion of voters voting democratic party vs those voting for the republicans in these polls was very similar and in many cases the same as the final results. The problem is that you made the assertion that the difference were far larger. I asked you to provide backup for that. We are still waiting. On Thu, Jun 6, 2013 at 12:04 PM, Sam <[email protected]> wrote: > > come on, you can't be arguing over this and not know anything about it can > you? > > > Yeah you can, nevermind. > . > > > > On Thu, Jun 6, 2013 at 9:09 AM, Larry C. Lyons <[email protected] > >wrote: > > > > > Nice story, any citations for that? Its nice making all those assertions > > (you'd think it was a TDD exercise) but you still have to back them up > Sam. > > > > > > On Thu, Jun 6, 2013 at 12:04 AM, Sam <[email protected]> wrote: > > > > > > > > I will try again. The left leaning polls over sampled dems by using the > > > high turnout of dems from 2008. That was rare and unlikely. The dems > > > actually showed up in lower numbers. However, since so few R's voted > the > > > polls were right in the end. This is not due to them being correct, > just > > > dumb luck that Romney would kill his base in the end. Between that and > > the > > > polls telling us Obam won, why bother voting? > > > On Jun 5, 2013 11:46 PM, "Scott Stroz" <[email protected]> wrote: > > > > > > > > > > > Let me see if I got this right: the polls that correctly predicted > the > > > > President winning were 'left leaning', but the one poll that > > incorrectly > > > > predicted Gov. Romney winning was accurate? > > > > > > > > > > > > On Wed, Jun 5, 2013 at 2:10 PM, Sam <[email protected]> wrote: > > > > > > > > > > > > > > But, the polls had 11+ D and more independents than normal. This > was > > to > > > > > mimic the high D turnout in 2008 which wasn't likely. However, the > > > > > extremely low R turnout gave them the correct numbers after all. > > > > > > > > > > I believe that's because Romney told voters he was the same as > Obama > > in > > > > the > > > > > last debate. > > > > > > > > > > . > > > > > > > > > > > > > > > On Wed, Jun 5, 2013 at 12:57 PM, Judah McAuley < > [email protected] > > > > > > > > wrote: > > > > > > > > > > > > > > > > > CNN exit polls from 2012: > > > > > > http://www.cnn.com/election/2012/results/race/president > > > > > > > > > > > > Voting break down by party: > > > > > > > > > > > > Democrats: 38% > > > > > > Republicans: 32% > > > > > > Independents: 29% > > > > > > > > > > > > So, yes, a 6% advantage in D vs R voting. > > > > > > > > > > > > And then Registered Voters via Pew: > > > > > > > > > > > > > > > > > > > > > > > > > > > http://www.people-press.org/2012/08/23/a-closer-look-at-the-parties-in-2012/ > > > > > > > > > > > > D: 35% > > > > > > R: 28% > > > > > > I: 33% > > > > > > > > > > > > If you push Independents to get which way they would lean in > voting > > > (D > > > > or > > > > > > R): > > > > > > > > > > > > D: 48% > > > > > > R: 43% > > > > > > > > > > > > So, a pretty consistent 5 to 7 percent margin no matter how you > > slice > > > > it. > > > > > > Hence why the (good) polls included more Democrat and > > > Democrat-leaning > > > > > > responses in their sample in order to match demographics. > > > > > > > > > > > > Cheers, > > > > > > Judah > > > > > > > > > > > > > > > > > > On Wed, Jun 5, 2013 at 6:14 AM, GMoney <[email protected]> > wrote: > > > > > > > > > > > > > > > > > > > > On Wed, Jun 5, 2013 at 8:09 AM, Larry C. Lyons < > > > > [email protected] > > > > > > > >wrote: > > > > > > > > > > > > > > > > > > > > > > > Very large scale surveys and the census have > > > > > > > > indicated that there are more Democratic than Republican > > voters. > > > > > > > > > > > > > > > > > > > > > > I was a little bit surprised to hear that. Larry, are you > talking > > > > about > > > > > > > REGISTERED voters, or people who actually cast votes? > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~| Order the Adobe Coldfusion Anthology now! http://www.amazon.com/Adobe-Coldfusion-Anthology/dp/1430272155/?tag=houseoffusion Archive: http://www.houseoffusion.com/groups/cf-community/message.cfm/messageid:364287 Subscription: http://www.houseoffusion.com/groups/cf-community/subscribe.cfm Unsubscribe: http://www.houseoffusion.com/groups/cf-community/unsubscribe.cfm
