US 2012 Presidential Election Polls

dttq · 06-11-2012 3:21am

What day and time will be know who has won the US election?

Ozymandius2011 · 06-11-2012 3:23am

Fivethirtyeight.com now placing Florida in the Obama column with a 52.5 probability.

Dttq in answer to your question we may or may not know for weeks depending on recounts, lawyers etc. If it's a blowout we should know early hours of morning. But there are likely to be many "Provisional (unverified) ballots" and in OH, they can't be counted until November 17th. In OH a recount follows automatically if the margin is 0.025% or less. 1% and a candidate can ask for one.

nagilum2 · 06-11-2012 3:37am

Ozymandius2011 wrote: »

Fivethirtyeight.com now placing Florida in the Obama column with a 52.5 probability.

Dttq in answer to your question we may or may not know for weeks depending on recounts, lawyers etc. If it's a blowout we should know early hours of morning. But there are likely to be many "Provisional (unverified) ballots" and in OH, they can't be counted until November 17th. In OH a recount follows automatically if the margin is 0.025% or less. 1% and a candidate can ask for one.

Is Silver off his rocker on FL? The RCP average (esp the most recent FL polls) do not seem to support that at all.

nagilum2 · 06-11-2012 3:54am

joseph brand wrote: »

Paddy Power:
Obama 2/9
Romney 3/1

If I stick a tenner on Obama I stand to come away with €12.22 /rubs hands

I thought they already paid out? Paddy Power confuses me.

Ozymandius2011 · 06-11-2012 3:58am

nagilum2 wrote: »

Is Silver off his rocker on FL? The RCP average (esp the most recent FL polls) do not seem to support that at all.

Well the Registered Dems are around 4% ahead in the early vote on a 52% turnout. Around 4.5 million people have voted early.

4,469,393
Party Reg
Dem 42.9%
Rep 39.1%
None/Oth 18.0%
Method
In-person 54.0%
Mail 46.0%
52.9%

nagilum2 · 06-11-2012 4:16am

Ozymandius2011 wrote: »

Well the Registered Dems are around 4% ahead in the early vote on a 52% turnout. Around 4.5 million people have voted early.

4,469,393
Party Reg
Dem 42.9%
Rep 39.1%
None/Oth 18.0%
Method
In-person 54.0%
Mail 46.0%
52.9%

That's a 3.8 spread - weak early voting figures for democrats.

In 2008, that spread for Obama was 9 points. That's Obama performing at -5 what he was four years ago, in a state that he only won by 2.8 points.
LINK: http://www.washingtonpost.com/blogs/the-fix/wp/2012/11/05/final-early-vote-numbers-suggest-a-very-close-race/

I think Silver is a great number cruncher, but he will get this one wrong. Bank on it.

If Paddy Power offered me odds on Romney taking Florida, I'd put A LOT on it.

southsiderosie · 06-11-2012 4:46am

nagilum2 wrote: »

That's a 3.8 spread - weak early voting figures for democrats.

In 2008, that spread for Obama was 9 points. That's Obama performing at -5 what he was four years ago, in a state that he only won by 2.8 points.
LINK: http://www.washingtonpost.com/blogs/the-fix/wp/2012/11/05/final-early-vote-numbers-suggest-a-very-close-race/

I think Silver is a great number cruncher, but he will get this one wrong. Bank on it.

If Paddy Power offered me odds on Romney taking Florida, I'd put A LOT on it.

The early voting period in Florida was shorter this election cycle than it was in 2008.

Ponster · 06-11-2012 4:47am

nagilum2 wrote: »

If Paddy Power offered me odds on Romney taking Florida, I'd put A LOT on it.

I think Silver is wrong here but I think that it's perhaps a lot closer in FL than you think. According to almost most polls Romney is leading FL by less than Obama is leading OH.

nagilum2 · 06-11-2012 4:48am

southsiderosie wrote: »

The early voting period in Florida was shorter this election cycle than it was in 2008.

The length of the period should not affect the ratio, only the volume, assuming uniform voting distribution throughout the period in question.

nagilum2 · 06-11-2012 5:23am

Ponster wrote: »

I think Silver is wrong here but I think that it's perhaps a lot closer in FL than you think. According to almost most polls Romney is leading FL by less than Obama is leading OH.

I'm sure it's close - Romney wouldn't be there on the last day otherwise - but I'd still play those odds above much else in this election.

I thought the silver model at 65% Obama was about right. He now has it at a 92% chance, though, and that feels like a far too aggressive probability to me.

If someone gave me Romney at 9/1, I'd definitely take that at this point!

southsiderosie · 06-11-2012 5:52am

nagilum2 wrote: »

The length of the period should not affect the ratio, only the volume, assuming uniform voting distribution throughout the period in question.

I don't think the volume is comparable because IIRC a Sunday was dropped - therefore, black churches missed an opportunity to do a 'Souls to the Polls' event, which is a disproportionately heavy voting day.

Duck Soup · 06-11-2012 12:51pm

Without veering into the voter suppression thread territory, the whole reason Republican legislatures - and only Republican legislatures - have been trying to curtail early voting is because it's used disproportionately by Democratic voters. And some days and times within the early voting periods are more heavily Democratic-loaded than others.

For example, if you cut off the weekend for early voting, lower income voters who cannot afford to take a weekday (or part thereof) off to vote may not be able to vote on the Tuesday. Plus as Rosie said, the Souls To The Polls drive on Sundays, used predominantly by African-American churches, is taken out of the equation.

You can also take more low income voters out of mix by curtailing voting during after-work hours on weekdays. So if, for example, you allowed early voting 10am-10pm in 2008 and now only allow it 10am-6pm, you will lose low income voters wanting to vote but not lose wages.

In a nutshell, if it didn't work at curbing the opposition's vote, they wouldn't do it.

Duck Soup · 06-11-2012 1:05pm

The final national polls before voting starts today.

seligehgit · 06-11-2012 6:10pm

Inquitus wrote: »

GOP tears are delicious, if you aren't a right wing religious whackjob, watching Obama win on Fox is tasty.

Any other right wing news stations you'd recommend that are on freesat?Is Fox available on line?

Amerika · 06-11-2012 6:19pm

seligehgit wrote: »

Any other right wing news stations you'd recommend that are on freesat?Is Fox available on line?

Actually a lot of us GOPers are planning on watching MSNBC tonight in order to see their pundits go into full mental meltdown.

Black Swan · 06-11-2012 7:41pm

Duck Soup wrote: »

The final national polls before voting starts today.

Most of these polls fall within a confidence interval of plus or minus 3, so if they fail to predict the election, later they may claim that they were not off, given that the reported numbers fell within this interval.

Ozymandius2011 · 07-11-2012 12:28am

CNN exit poll:
Democrats 37%
Republicans 34%
Independents 29%

Dems: Obama 92, Romney 7
Reps: Romney 92, Obama 5

Conservatives: Romney 85, Obama 15

Urban people: 62-38 for Obama
Rural people: 62-38 for Romney.

Independents: 60-40 for Romney.

---
The exit poll debunks Rasmussen polls that say there are 1% more Reps than Dems.

---
CNN (Ohio) ezit poll:
Getting better 37%
Worse 33%

--
Better on economy:
Romney 48
Obama 47

---
Virginia:
Economy: romney 53, Obama 45
Satisfied+Enthusiastic = 50%
Angry+ Dissatisfied = 48%

TwoShedsJackson · 07-11-2012 1:55pm

So let's see how the only pollsters Amerika trusts, Rasmussen, got on with their polling predictions:

Nationally, Rasmussen polled at 49%-48%. The actual result was (so far) 50%-49% Obama, the reverse of Rasmussen's poll.

In Colorado, Rasmussen polled at 50%-47% for Romney. The actual result was 51%-47% for Obama, the reverse of Rasmussen's poll.

In Florida, Rasmussen polled at 50%-48% for Romney. The actual result was 50%-49% for Obama, the reverse of Rasmussen's poll.

In Iowa, Rasmussen polled at 49%-48% for Romney. The actual result was 52%-47% for Obama, the reverse of Rasmussen's poll, doubled.

In New Hampshire, Rasmussen polled at 50%-48% for Romney. The actual result was 52%-47% for Obama, the reverse of Rasmussen's poll.

In Ohio, Rasmussen polled at a 49%-49% tie. The actual result was 50%-48% for Obama, a two-point swing.

In Virginia, Rasmussen polled at 50%-48% for Romney. The actual result was 50%-48% for Obama, the reverse of Rasmussen's poll.

In Wisconsin, Rasmussen polled at a 49%-49% tie. The actual result was 52-47% for Obama, a six-point swing.

In other words, in all the races that mattered, Rasmussen got it egregiously wrong. They didn't call a single battleground state right except for North Carolina, and even there it appears that they overestimated the margin of Romney's win.

Duck Soup · 07-11-2012 2:34pm

Rasmussen relied solely on automated calls to landlines. They might want to revisit their adherence to that model.

cristoir · 07-11-2012 2:51pm

Silver was spot on.

Brian? · 07-11-2012 4:26pm

So in 4 years time can we agree just to accept what Nate Silver and the RCP average say? It'll save an awful lot of fretting and worrying.

Black Swan · 07-11-2012 4:41pm

Duck Soup wrote: »

Rasmussen relied solely on automated calls to landlines. They might want to revisit their adherence to that model.

If I recall, there were approximately 26 percent of Americans that did not have landlines, only mobiles, and such mobile-only people had demographic characteristics that differentiated them from those with landlines. Rasmussen's method could produce systematic error and bias their samples. Perhaps this accounted for their polls tending to favour Romney during past months, producing a "Dewey Wins" effect?

FatherTed · 07-11-2012 4:45pm

Wow Rasmussen was way off. I wonder who's been paying him to give false hope to Romney and the Republicans when the other polls got it pretty much right. Oh and welcome to the 21st century, people use cell phones now.

Brian? · 07-11-2012 4:45pm

Black Swan wrote: »

If I recall, there were approximately 26 percent of Americans that did not have landlines, only mobiles, and such mobile-only people had demographic characteristics that differentiated them from those with landlines. Rasmussen's method could produce systematic error and bias their samples. Perhaps this accounted for their polls tending to favour Romney during past months, producing a "Dewey Wins" effect?

You know what, I'd say 100% of seniors do have land lines. That could have skewed Rasmussen's polls in favour of Romney.

Duck Soup · 07-11-2012 4:54pm

Not calling mobiles in this day and age is insanity for a pollster, almost guaranteed to give an older, Republican-leaning 'house effect'. The aggregators like Nate Silver and Sam Wang at the Princeton Election Consortium can tweak their models to weight against each pollster's house effect (read: bias), but it's surprising that Rasmussen (and Gallup) didn't weight differently themselves.

Automated calling (introduced by Rasmussen to save money) also gets responded to more by older people - younger people are more likely just to put the phone down if it's not a live person on the other end - so that kind of compounded the problem.

07-11-2012 4:59pm

The cell-only issue has been flagged since at least 2004 that I can think of. I really don't understand why people insisted for so long that the result was in any doubt.

Black Swan · 07-11-2012 5:00pm

Duck Soup wrote: »

Automated calling (introduced by Rasmussen to save money) also gets responded to more by older people - younger people are more likely just to put the phone down if it's not a live person on the other end - so that kind of compounded the problem.

Mobile call IDing, call blocking, voice mail, etc., could have filtered out automated calls. It had also been reported that only 1 in 10 called replied to the surveys, cutting out 90 percent of the sample originally selected.

Mobile-only without landlines is rapidly growing in the US too, so in another 2 to 4 years, the "Dewey Wins" effect of Rasmussen could be larger if they do not markedly change their sampling methodology.

seligehgit · 07-11-2012 5:18pm

cristoir wrote: »

Silver was spot on.

Yeah called all 50 on the money.

Ozymandius2011 · 07-11-2012 10:11pm

Rasmussen shown to have been a bit too bearish on Obama. While not acknowledging this, they hint at it (likely alluding to the cell phone issue) here:

This race was very likely the last presidential election of the telephone polling era. While the industry did an excellent job of projecting last night’s election, entirely new techniques will need to be developed before 2016. The central issue is that phone polling worked for decades because that was how people communicated. In the 21st century, that is no longer true.

Rasmussen was not far off on the national popular vote but was dreadful in some state polls, like NC, Wisconsin, Iowa and Florida where they overestimated the GOP vote considerably.

Black Swan · 08-11-2012 11:51pm

Both Rasmussen and Gallup polls favoured Romney during the past month up to the election. They will have to rethink their sampling methods before 2014 midterms, or potentially suffer the same fate again with Congressional races.

Silver gained a lot of credibility in this election. His prediction model had been superior to Rasmussen and Gallup.

Ozymandius2011 · 09-11-2012 6:38am

Final Rasmussen polls v actual results:

Ohio -- Rasmussen: dead heat. Actual: Obama by 2.

Virginia -- Rasmussen: Romney +2. Actual: Obama by 3.

Iowa -- Rasmussen: Romney +1. Actual: Obama by 6.

Wisconsin -- Rasmussen: tie. Actual: Obama by 7.

Colorado -- Rasmussen: Romney +3. Actual: Obama by 5.

Also apparently PPP was the most accurate pollster which is remarkable as they are Dem-aligned.

darjeeling · 09-11-2012 10:15am

Ozymandius2011 wrote: »

Final Rasmussen polls v actual results:

Ohio -- Rasmussen: dead heat. Actual: Obama by 2.

Virginia -- Rasmussen: Romney +2. Actual: Obama by 3.

Iowa -- Rasmussen: Romney +1. Actual: Obama by 6.

Wisconsin -- Rasmussen: tie. Actual: Obama by 7.

Colorado -- Rasmussen: Romney +3. Actual: Obama by 5.

Also apparently PPP was the most accurate pollster which is remarkable as they are Dem-aligned.

All true.

The final 2 weeks' swing state polling data from all pollsters shows Rasmussen to have a strong pro-Republican bias. They published 14 polls with a mean lean to Republicans of over 4 points when compared to the actual election results.

Gravis Marketing (whose credibility as a genuine pollster has been questioned - link), was also biased towards Republicans, though not so much (2.6 point average in 13 polls).

PPP did not show any systematic bias in their 18 swing state polls. Their polls had an average difference of 0.3 points (in Republican favour) from the actual election results.

Pollster No. polls Mean poll - vote difference Range
ARG 4 REP+4.5 (REP+6.6 .. DEM+0.1)
Rasmussen Reports 14 REP+4.2 (REP+7.7 .. REP+0.2)
Gravis Marketing 13 REP+2.6 (REP+5.8 .. REP+0.6)
Purple Strategies 3 REP+2.2 (REP+3.7 .. DEM+0.1)
NBC/WSJ/Marist 8 REP+1.5 (REP+4.7 .. DEM+4.1)
New England College 3 REP+1.5 (REP+2.8 .. DEM+0.2)
WeAskAmerica 6 REP+1.1 (REP+3.6 .. DEM+2.1)
CNN/Opinion Research 4 REP+0.3 (REP+2.7 .. DEM+2.1)
PPP (D) 18 REP+0.3 (REP+3.8 .. DEM+3.1)
SurveyUSA 4 DEM+0.2 (REP+2.8 .. DEM+3.1)
CBS/NYT/Quinnipiac 3 DEM+0.8 (REP+1.0 .. DEM+3.1)

Edit: all data from RCP (http://www.realclearpolitics.com/epolls/latest_polls/president/ and http://www.realclearpolitics.com/elections/live_results/president/)

09-11-2012 5:42pm

The Rasmussen bias was known ages ago, the lad on electoral-vote.com kept a separate page going for the last 4 or 5 weeks excluding Rasmussen polls.

Duck Soup · 09-11-2012 6:19pm

Just worth noting that both Nate Silver at FiveThirtyEight and Drew Linzer at Votamatic called all 51 electoral college races (50 states plus District of Columbia) correctly and Sam Wang at the Princeton Election Consortium called 50 out of 51 correctly, with Florida his sole miscall.

I just wanted to lay out the remarkable accuracy of the poll aggregators so in 4 years time, we're not sitting here saying "Rasmussen/CNN/Gallup/Ipsos/YouGov has Chris Christie 19 points ahead/behind." The aggregators hace shown their worth and perhaps someone might care to mention this to Joe Scarborough the next time he has a sudden rush of blood to the ego and calls them "jokes" because they don't tell him what he wants to hear or believe.

darjeeling · 09-11-2012 6:49pm

Here's a fuller dataset from http://electoral-vote.com/

102 swing state polls within final 2 weeks from pollsters producing at least 4 polls. ARG, Rasmussen, Gravis and Pulse Opinion all showed a pro-Republican bias. Zogby, SurveyUSA, PPP, and ORC Intl showed no bias. Non-swing state polling was a slightly different story, but not of much importance in predicting who was going to win.

As others have said, the aggregators did indeed do a remarkable job of predicting the outcome, successfully correcting for biases where they occurred. They also got well ahead of the columnists in identifying when momentum shifted in the race; Republican spinners were still claiming momentum for Romney almost two weeks after the poll aggregators showed he was going backwards.

Pollster Polls Mean polling error (MPE) in points MPE standard error prob. no bias
ARG 4 REP+4.5 1.5 0.06
Rasmussen 14 REP+4.2 0.6 6E-06
Gravis Marketing 13 REP+2.6 0.5 2E-04
Pulse Opinion Research 5 REP+2.5 0.9 0.06
Marist Coll. 8 REP+1.5 1.1 0.22
IPSOS 12 REP+1.1 0.8 0.19
PPP 27 REP+0.3 0.4 0.45
ORC International 4 REP+0.3 1.1 0.82
SurveyUSA 8 REP+0.2 0.9 0.82
Zogby 7 REP+0.1 1.7 0.93

Raphael · 09-11-2012 8:12pm

It's a little interesting that there are no pollsters that had a democratic bias, and all the unbiased ones had a slight republican leaning. I'm not trying to conspiracy theorize - it's more likely to be related to old fashioned methodologies targeting old fashioned voters better (who tend to be republican voters) - but it begs the question of whether this shows that pollsters need to get their act together and try to find a way to target young people.

(It's also possible that the flaw is caused by another demographic split, mind you. THe age one just seems more likely, since it's pretty likely that's why Rasmussen were so off)

darjeeling · 09-11-2012 8:35pm

Raphael wrote: »

It's a little interesting that there are no pollsters that had a democratic bias, and all the unbiased ones had a slight republican leaning. I'm not trying to conspiracy theorize - it's more likely to be related to old fashioned methodologies targeting old fashioned voters better (who tend to be republican voters) - but it begs the question of whether this shows that pollsters need to get their act together and try to find a way to target young people.

(It's also possible that the flaw is caused by another demographic split, mind you. THe age one just seems more likely, since it's pretty likely that's why Rasmussen were so off)

The slight bias in the main group of pollsters could actually be due to Obama picking up a few extra voters in the closing days, perhaps people who approved of his handling of the response to storm Sandy. Outside the swing states, Obama did out-perform his polls in North-Eastern states in the path of the storm, notably New Jersey.

There was a clever analysis of the different polling companies by Drew Linzer of votamatic.org, showing they essentially split into two groups - a small number of multi-polling firms (Rasmussen, ARG and Gravis) favouring Romney, and a much bigger group of the rest of the major firms plus all the one-off pollsters, who collectively scored the race around 1.5 points more in Obama's favour (link). While there were some small house effects amongst the main group, there weren't any that seemed to show a
pro-Obama bias anything like the pro-Romney bias of Rasmussen et al.

The actual results now show - unsurprisingly - that the mainstream pollsters were right.

LuckyLloyd · 09-11-2012 8:40pm

Black Swan wrote: »

Both Rasmussen and Gallup polls favoured Romney during the past month up to the election. They will have to rethink their sampling methods before 2014 midterms, or potentially suffer the same fate again with Congressional races.

Silver gained a lot of credibility in this election. His prediction model had been superior to Rasmussen and Gallup.

That's quite the understatement! He nailed the Presidential election to the wall.

Ozymandius2011 · 09-11-2012 10:39pm

darjeeling wrote: »

Here's a fuller dataset from http://electoral-vote.com/

102 swing state polls within final 2 weeks from pollsters producing at least 4 polls. ARG, Rasmussen, Gravis and Pulse Opinion all showed a pro-Republican bias. Zogby, SurveyUSA, PPP, and ORC Intl showed no bias. Non-swing state polling was a slightly different story, but not of much importance in predicting who was going to win.

As others have said, the aggregators did indeed do a remarkable job of predicting the outcome, successfully correcting for biases where they occurred. They also got well ahead of the columnists in identifying when momentum shifted in the race; Republican spinners were still claiming momentum for Romney almost two weeks after the poll aggregators showed he was going backwards.

Pollster Polls Mean polling error (MPE) in points MPE standard error prob. no bias
ARG 4 REP+4.5 1.5 0.06
Rasmussen 14 REP+4.2 0.6 6E-06
Gravis Marketing 13 REP+2.6 0.5 2E-04
Pulse Opinion Research 5 REP+2.5 0.9 0.06
Marist Coll. 8 REP+1.5 1.1 0.22
IPSOS 12 REP+1.1 0.8 0.19
PPP 27 REP+0.3 0.4 0.45
ORC International 4 REP+0.3 1.1 0.82
SurveyUSA 8 REP+0.2 0.9 0.82
Zogby 7 REP+0.1 1.7 0.93

A surprisingly good election year for Zogby, hitherot referred to by Nate Silver as "the worst pollster in the world".

darjeeling · 09-11-2012 11:27pm

Ozymandius2011 wrote: »

A surprisingly good election year for Zogby, hitherot referred to by Nate Silver as "the worst pollster in the world".

Zogby's polls (on-line rather than phone polls, hence the criticisms) had much bigger margins of error than the PPP and other firms' polls, but not the systematic bias seen for Rasmussen.

The Zogby polls up on the Electoral Vote site seem to be only a snapshot of the full tracking polls (not sure why that is), and neither RCP nor Nate Silver used them at all. Silver did though use the Gravis polls, which Electoral Vote chose not to use.

Very complicated, this polling business!

nagilum2 · 09-11-2012 11:37pm

darjeeling wrote: »

Zogby's polls (on-line rather than phone polls, hence the criticisms) had much bigger margins of error than the PPP and other firms' polls, but not the systematic bias seen for Rasmussen.

The Zogby polls up on the Electoral Vote site seem to be only a snapshot of the full tracking polls (not sure why that is), and neither RCP nor Nate Silver used them at all. Silver did though use the Gravis polls, which Electoral Vote chose not to use.

Very complicated, this polling business!

I thought Silver would nail everything except FL and VA, maybe CO. He definitely earned my respect in this cycle (and I already respected his number crunching abilities a lot).

Ozymandius2011 · 10-11-2012 12:26am

The SC is due to hear a challenge to the part of the 1965 Voting Rights Act requiring mostly Southern states to get permission from the DOJ before changing electoral-laws. Chief Justice John Roberts (of Texas) has expressed concerns it may be outdated, despite the fact that the Bush DOJ had to intervene when Shelby County, Alabama violated the Act in 2005. Not surprisingly, that is the county making the challenge.

There were reports in Alabama that road-blocks were placed around a polling-station in an African-American area.

US 2012 Presidential Election Polls

Comments