After you do all the math and the calculating, don’t forget to add in the commons sense factor that tells you whether democrat turnout will be like it was in 2008, or much smaller than in 2008.
Dirty secret - no way to independently verify the accuracy of a poll 2 months from an election.
They can say any crazy thing they want. Who’se to gain say ‘em? Me,
http://www.unskewedpolls.com/
There is much work to do. Romney needs to talk details of his plans. I dont want to hear him say one more time that he knows what to do. Please tell us what that is!!!
Good plan of how Romney could turn things around can be found here.
http://www.realitybatslast.com/2012/09/27/how-romney-can-win-with-a-mandate/#comments
AS I have posted before, the real polls, that is the ones that are highly accurate, are something you will not see. At least not for many years.
I trained as a pollster in college, worked as one afterwords.
The polls you see in the media are all about either rallying the faithful or demoralizing the opposition or selling eyeballs.
The actual polls, that is the ones where the outcome actually resembles reality as closely as (lots of ) money and (woefully limited and stressed out) time permit. These polls are the ones the campaigns (or their ancillary staffs, usually funded by PACs) use to determine where to buy ads or otherwise apply resources. As Willard pointed out it’s the small percent in the middle that “matter” (in terms of where you spend money, and that, my friend is the only thing that matters in a campaign). You, me. Jim Rob, Anderson Cooper, John Sterwart, Rush... no one sees those ‘real’ polls except a very very small group around the candidate, they are crucial info. If you have $400K in a tri-county area, NOW do you spend it? That is what the $$$ and the genuine expertise are chasing right now. News organizations and the campaighns release “polls” all the time, but it’s all about psych ops and selling papers/website hits, the numbers are all about what will generate excitement (or despair).
My old buds are making the mortgage, college and boat payments for the next few years over the course of the next few weeks. And they care far more about being right than who wins.
I don’t know much about polling, but I do have experience with data analysis.
If your raw data is not random and you have to apply some modeling formula to correct your data, then the data is pretty much worthless. If polling data represented a random sample of the population it was representing, no correction would be necessary.
If you have a known quantifiable systematic error then you can correct for that error (i.e. you have a bad measuring sensor and you know it produces a constant error).
I think a good guess with good intuition can give as good a result as most of the pollsters. You know Obama is not going to do as well as 2008 and it is likely Romney will do better than McCain.
If Obama wins it will be by a closer margin than 2008. At this point, there is nothing other than questionable polling that says Romney will lose.
NONE of them are legitimate they are all propaganda.. or worse agitprop..
Even the ones that favor your “issue(s)”..
Even simple questions are not so simple..
Ditzes are manipulated by Polls, to everyone else they are entertainment..
Just vote your heart, ignore the polls. The polls are rigged to influence your vote by making use of the “herding instinct”.
Personally, I think the only polls that are relavant are those that translate their numbers to Electoral votes.