Posted on 11/05/2012 5:45:49 AM PST by kevkrom
Okay... election day is tomorrow, and it's time for all us to make final predictions on the record... you know, for bragging rights.
This is specifically for the Presidential race, but if you want to lock in overall and/or specific Senate and House races for "bonus points", by all means go ahead!
DING! DING! DING! WE HAVE A WINNER!!!
I’m guessing there’s at least a 40 percent chance of you being right. :-(
It may very well be garbage in, garbage out tomorrow but it is very, very unlikely. These polling outfits know what they are doing, they are professional statisticians and social scientists. It would be an insane statistical anomaly for 40 or so polling outfits to all be getting similar results....we’re talking 1 in millions. The only alternative is that the thousands of employees of all the polling outfits are involved in a very large conspiracy to depress the conservative vote but keeping that quiet when the incentive to leak is so high is probably 1 in a quadrillion.
Sample sizes of Party ID do not get ridiculous to me unless people screw with them too much..aka...weighting. One thing I have tried over and over and over to get across to people is that Party ID is an attitude or a feeling, NOT a rigid identity like American or Canadian or Black or White or Hispanic. The mushy middle will call themselves Republican or Democrat VERY often based on how they vote. The party ID FOLLOWS the vote and not the other way around.
In other words, if Bush is up 5 points against Kerry in Oct 2004, you will see a Dem party ID advantage of only 3 points. If Obama is up 7 points in Oct 2008 you see a Dem party ID advantage of 6 or 7 points and if you see the Republicans up 6 points in the 2010 elections you see party ID tied.
The party ID is very fluid and not rigid at all and to screw with it too much, you risk becoming the outlier. This is exactly what Gallup and Rasmussen did in 2010:
http://www.realclearpolitics.com/epolls/other/2010_generic_congressional_vote-2171.html
As you can see, Gallup and Rasmussen were way off that year. They saw the enthusiasm gap in their data and over-corrected the party ID thinking there MUST be a republican advantage when the party ID was actually tied. But since dems usually outnumber republicans in registration by 3 to 10 points historically for over 30 years, a party ID tie was a HUGE advantage for Republicans already...there was NO NEED to weight the data.
Rasmussen and Gallup are doing the same thing this year and tomorrow we will see if they screwed up again or are doing something novel and genius. I honestly think they are screwing up, they will be off by at least 3 points (possibly more) based on what I’ve plugged in to SPSS many times today.
Your comparison of a congressional race and presidential race is invalid. They are two different animals.
Rasmussen and Gallup are two of the most accurate pollsters for presidential elections.
Are you aware Rasmussen was the MOST ACCURATE for the 2008 presidential election?
You’re giving the pollsters too much credit. Most of these pollsters are run by liberal newspapers. Party identification is VERY IMPORTANT. So is enthusiasm.
Obama doesn’t reach 47percent. East states have liberal strong holds report immediately to create illusion that Obama is leading. Media calls many states for Obama immediately though they later go for Romney. Media stalls and delays so west coast elections don’t wash out. Maine and new Hampshire numbers tip the hand that GOP is going to win big. Media effort helps dems retain senate by one. Ohio is a blowout and penn and wis are small margin, but big enough wins for mitt. Romney gets 53 percent nationally.
Stepped into the voting booth and drew the curtain. Later that evening a winner was announced and that was it! No drama, no attorneys, no recounts. No one threatened to riot. How I long for those days.
I think your map is likely to be 100percent. Though pa might go red..
They aren’t run by the newspapers, they are hired by the newspapers. And if they do a bad job, they don’t get hired the next time. Fox has fired a few pollsters over the last decade because of bad results. They dropped Rasmussen after 2010. They now have 2 of the most reputable outfits in all of polling working for them.
And Rasmussen did indeed do great in 2008 but he wasn’t the most accurate. He had Obama +6 and Obama won +7.3. He was actually tied for 7th best. He was the most consistent in the entire month of October but there is no way to know if his polls were right or wrong all that month. The last poll before the election is how you can best judge accuracy.
These pollsters did as well as Rasmussen: George Washington University and Pew Research, both showing Obama +6, same as Rasmussen. Rasmussen, GWU and Pew were off by 1.3 points.
And these outfits did BETTER than Rasmussen: NBC News, Fox News, CNN/OR and Ipsos/McClatchy, IBD/TIPP, Gallup (traditional):
Not sure how you can look at the last polls done by each outfit shown in that link and say Rasmussen was the best.
Romney 278
Obama - 260
Romney wins - Florida, Georiga, South Carolina, North Carolina, Alabama, Mississippi, Louisiana, Texas, Arkansas, Kansas, Tennessee, Kentucky, West Virginia, New Hampshire, Alaska, Utah, South Dakota, North Dakota, Wyoming, Idaho, Nebraska, Iowa, Montana, Oklahoma, Missouri, Arizona, Indiana, Virginia, and Wisconsin.
He loses PA, OH, CO, and NV
Obama 39%, Romney 59%, in the popular vote, and 140 to 398 electoral votes.
Breaking information indicates wider margins, but I'll stick with those numbers since few others want to go this bold.
Romney is getting Independents by 22 points, when Obama took Independents by +8 points in 2008. That's a huge shift among almost a full third of the electorate.
Obama is down in every other demographic category from his 2008 percentages, but the Independents are the biggest group, and that 30 percentage shift from D to R alone among Independents is sufficient to justify my 20 point total difference.
Obama is down 10 Million in early voting compared to his early voting total in 2008. I'd bet he'll lose another 10 Million votes on election day from his 2008 election day totals.
Over several states, about 10 Million bogus registrations have been purged from the voter rolls. Late-night poll workers can't ghost-vote if the names are not on the rolls, and it takes a lot of footwork to recreate those 10 Million bogus registrations. They may have tried, but I don't think they got anything close to that.
Stevie Wonder can't draw a crowd for Obama; the "Born in the USA" dude can't draw a crowd for Obama; people in Virginia listened to Clinton yesterday, then started walking out when Obama started talking. Blacks in Chicago, Cleveland, Toledo, and every other inner city aren't turning out for this fraud. During the convention, they couldn't fill a bus in NC for the fraud; went to SC and still couldn't fill a bus; went 300 miles to Atlanta, and still had to pay people to get on the stinking bus. Black folks are done with this fraud. He ain't got nothing else but the union and government slugs, and the commie media, and they can't even fill a bus for this fraud.
There's tens of thousand of Mexicans who have died in the border wars during the reign of this fraud, and he's gonna get the Latino votes? Maybe some, but not like 2008.
The 2010 midterm election was just a warm-up; 2012 is D-Day, the Bulge, and the march to Berlin.
Other than that ...
So Barone is risking his reputation to sell papers? Doubt it. We will soon see who was right,who was wrong.
Post Romney victory : team OBAMA starts to SHRED, DUMP & DESTROY all records and evidence of the regime’s criminal corruption.
Reagan was the lesson but what followed was worthless, Republican and Democrat.
Oh my gosh! We’re doomed!
I guess Rats +11 is what we’re looking at for this election, because by golly that’s what CNN has, and they are the experts!
Would you like to buy some ocean front property in New Jersey?
“So Barone is risking his reputation to sell papers? Doubt it. We will soon see who was right,who was wrong.”
He’s not risking anything. People will still read him whether he is right or wrong. The list of pundits with a really really crappy track record that still gets lots of views is quiet a long list.
“
Oh my gosh! We’re doomed!
I guess Rats +11 is what we’re looking at for this election, because by golly that’s what CNN has, and they are the experts!
Would you like to buy some ocean front property in New Jersey?”
Actually no, NBC/WSJ has Dems +2 and I think it will be right around +2 to +3 Dems based on the consistency of 12 major national polls saying similar things.
I have completely removed emotion and done my best to remove all personal bias as I plug the data into various regression analyses...and this looks just like 2004 but with Obama in Bush’s position.
If it’s +2 or +3 Rats, then we are going to win. Absolutely no question in my mind. That is significantly less than what the models for most polls have been at.
You are in error about what most polls are sampling at. Most polls have been at +8 Rats, which is ridiculous.
So based upon what you’re telling me would be the sample, it should be a +5-6 Romney win. But I am predicting +4.
You freaking NAILED the projection.
“You freaking NAILED the projection.”
3 outfits muddied the waters for all of us. Rasmussen, Gallup and RealClearPolitics. I will never trust any of those three again.
Rasmussen fundamentally does not understand party ID and spread his ignorance all over FR and in the conservative blogs, FoxNews, Rush, Drudge, everywhere...it was like poison.
You sample 1000 people and 38% say they are Democrats and 32% say they are Republicans...you leave it at that! Party ID FOLLOW the vote, not the other way around. Rasmussen weighted and fudged the data to fit the way he saw the world. No one person sees the world as it objectively is, Philosophy 101.
RealClearPolitics threw out any polls they saw as from “biased” sources without looking at their methodologies. DailyKos (Obama +2) had incredibly good methodology and will go down as the best or nearly the best poll of Nov. 2012. But the people running RealClearPolitics are conservative, and I love that about them, but you don’t bring your ideology into the scientific realm....period.
They did the same thing to PPP. Liberal outfit, throw them out, they aren’t going in our RCP average. PPP ended up the same as DailyKos, dead on at Obama +2.
Lastly, Gallup. Gallup has been a joke for almost a decade now. In 2010 they’re final poll was so embarrassing I don’t know how or why ANYONE would ever post their results. They called the generic +15 Republicans and were dead last, off by over 8 points. They are possibly the worst polling outfit so far in the 21st century.
So you take the fact that RCP throws out polls that are from liberal sources without any scientific justification. Ignore RCP during the election but start paying attention to their average toward the end when they start allowing more polls into the average.
Throw out Rasmussen completely because A) he uses automated phone calls B) he only calls landlines and C) he tinkers with party ID.
Lastly throw out Gallup because they were such an insane outlier that no one with common sense would have considered their polls. If you have 12 polls saying the race is tied +/- 2 and Gallup, one single poll, is saying Romney is up +5. That’s a no brainer.
Of course I did some historical research and look at the census data for 2010 to get my projection as well. The census data was amazing. It told me that the 2008 youth and hispanic votes were not a fluke. The millenials, the youth now, are a larger population than the baby boomers...I didn’t know that until I looked at the census. The hispanic vote is growing at insane rates and the black vote is solid 13% and their turnout is pretty much the same.
Add all that up, it wasn’t tough to project what I did. I will tell you what was tough, POSTING IT HERE! I got by teeth kicked in by a lot of people.
I have to mention one more thing. My utter disdain for Matt Drudge and his political quackery. He lead us all on and his cherry picking polls and giving false hope bled into the campaigns and the volunteers minds. It could have negatively affected the get out the vote efforts.
Drudge could have chosen from any of 18 polls to put on his website. There were 18 solid firms to choose from and here is how they did when compared to the final results. I have listed them in order from most accurate to least accurate:
Ipsos/Reuters - Obama +2
PPP - Obama +2
DailyKos - Obama +2
YouGov - Obama +2
Pew - Obama +3
ABC/Wash Post - Obama +3
Angus-Reid - Obama +3
ABC/Post - Obama +3
UPI/CVOTER - Obama +1
IBD/TIPP - Obama +1
Gravis Marketing - tie
JZ Analytics/Newsmax - tie
Politico/GWU/Battleground - tie
Monmouth - tie
ARG - tie
CNN - tie
Rasmussen - Romney +1
Gallup - Romney +2
Guess which two polls Drudge put on his website nearly every damn day for the last week. You guessed, the bottom 2. He chose the two most inaccurate pollsters, the obvious outliers to anyone that has had even intro to statistics, on to his page. That really pissed me off because of the meme that it created that everything would be fine and no more phone calls or door knocking were necessary.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.