Poll Analysis: Even more Ryan bump

ObamaRomney
96.9% probability of winning 3.1% probability of winning
Mean of 302 electoral votesMean of 236 electoral votes

The previous analysis showed G.O.P. presidential candidate Mitt Romney edging up to almost a 1% probability of winning an election held now. Romney lagged in expected electoral votes to President Barack Obama by 230 to 308.

Since then, 15 new polls covering 12 states have been released.

startendsample%%%
stpolldatedatesizeMOEORdiff
COKeating21-Aug22-Aug5004.44844O+4
CTQuinnipiac22-Aug26-Aug14722.65245O+7
CTPPP22-Aug23-Aug8815340O+13
FLCNN/TIME22-Aug26-Aug8953.55046O+4
IAPPP23-Aug26-Aug12442.84745O+2
MIMitchell23-Aug23-Aug12772.746.646.7R+0.1
MOMason-Dixon22-Aug23-Aug6254.04350R+7
MORasmussen22-Aug22-Aug5004.54746O+1
NVPPP23-Aug26-Aug8313.45047O+3
NJEagleton-Rutgers23-Aug25-Aug7103.55137O+14
NCCNN/Time22-Aug26-Aug7663.54748R+1
NCSurveyUSA18-Aug23-Aug5404.34343tie
OHColumbus Dispatch15-Aug25-Aug17582.14545tie
PAPhiladelphia Inquirer21-Aug23-Aug6014.05142O+9
VARasmussen23-Aug23-Aug5004.54747tie

Obama takes the latest Colorado poll by +4% over Romney, and he leads in four of the five current polls for the state.

Two polls in Connecticut both go to Obama. The Quinnipiac poll has Obama up by a modest +7%. A slightly older PPP poll has Obama up by +13%.

The latest Florida poll has Obama leading Romney by +4%. The current Florida polls go 4 to 2 for Romney, and Romney is given a 97% chance of winning the state right now.

Obama is up by +2% in the new Iowa poll. The candidates split the two current polls, but the poll that has Obama up is the much larger of the two: ObamaRomney29Jul12-29Aug12Iowa

In Michigan, Romney leads Obama by a weak +0.1%. The candidates split the four current polls, but the weight of the evidence has Obama up slightly with a 57% probability of winning an election held now.

The candidates split the two Missouri polls, with Romney up by +7% in one and Obama up by +1% in another. Obama has only led in this one poll out of the 6 current Missouri polls: ObamaRomney29Jul12-29Aug12Missouri

Nevada has Obama up by a slender +3% over Romney, slightly beating the +2% he had in the other current poll: ObamaRomney29Jul12-29Aug12Nevada

Little surprise that New Jersey has Obama up by a double-digit lead (+14%) over Romney.

In North Carolina, Romney has a +1% lead over Obama in one poll and the candidates are tied in another. The weight of evidence in the five current polls has Romney up by the slightest margin and a 56% probability of taking the state in an election held now:
ObamaRomney29Jul12-29Aug12North Carolina

Ohio is a tie at 45% each in the new poll. But Obama has led in three of the current six polls (with two ties), so the weight of evidence gives him an 87% probability of taking the state right now:
ObamaRomney29Jul12-29Aug12Ohio

Another Pennsylvania poll gives Obama a +9% lead over Romney. Obama take all three of the current polls and would be expected to win an election now with a 99% probability.

Virginia is all tied up at 47% in the newest poll. Overall, Obama takes 4 of the six current polls, so he ends up with a 90% probability of winning an election held now.

Now, after 100,000 simulated elections, Obama wins 96,863 times and Romney wins 3,137 times (including the 449 ties). Obama receives (on average) 302 (-6) to Romney’s 236 (+6) electoral votes. In an election held now, we would expect Obama to win with a 96.9% (-2.3%) probability and Romney with a 3.1% (+2.3%) probability.

Electoral College Map

AlabamaAlaskaArizonaArkansasCaliforniaColoradoConnecticutDelawareFloridaGeorgiaHawaiiIdahoIllinoisIndianaIowaKansasKentuckyLousianaMaineMarylandMassachusettesMichiganMinnesotaMississippiMissouriMontanaNebraskaNevadaNew HampshireNew JerseyNew MexicoNew YorkNorth CarolinaNorth DakotaOhioOklahomaOregonPennsylvaniaRhode IslandSouth CarolinaSouth DakotaTennesseeTexasUtahVermontVirginiaD.C.WashingtonWest VirginiaWisconsinWyoming

Electoral College Map

GeorgiaAlaskaArizonaArkansasCaliforniaColoradoDelawareConnecticutFloridaMississippiAlabamaHawaiiIdahoIllinoisIndianaIowaKansasKentuckyLouisianaMaineMarylandMassachusettsMichiganMinnesotaMissouriMontanaNebraskaNevadaNew HampshireNew JerseyNew MexicoNew YorkNorth CarolinaNorth DakotaOhioOklahomaOregonPennsylvaniaRhode IslandSouth CarolinaSouth DakotaTennesseeTexasUtahVermontVirginiaD.C.WashingtonWest VirginiaWisconsinWyoming

Here is the distribution of electoral votes [FAQ] from the simulations:

Ten most probable electoral vote outcomes for Obama:

  • 306 electoral votes with a 3.67% probability
  • 312 electoral votes with a 3.55% probability
  • 297 electoral votes with a 3.37% probability
  • 296 electoral votes with a 3.11% probability
  • 303 electoral votes with a 2.77% probability
  • 313 electoral votes with a 2.66% probability
  • 307 electoral votes with a 2.50% probability
  • 302 electoral votes with a 2.34% probability
  • 311 electoral votes with a 2.31% probability
  • 287 electoral votes with a 2.23% probability

After 100,000 simulations:

  • Obama wins 96.9%, Romney wins 3.1%.
  • Average (SE) EC votes for Obama: 301.6 (17.4)
  • Average (SE) EC votes for Romney: 236.4 (17.4)
  • Median (95% CI) EC votes for Obama: 302 (268, 335)
  • Median (95% CI) EC votes for Romney: 236 (203, 270)

Each column of this table shows the electoral vote total aggregated by different criteria for the probability of winning a state (Safe=100%, Strong=90%+, Leans=60%+, Weak=50%+):

ThresholdSafe+ Strong+ Leans+ Weak
Safe Obama119
Strong Obama118237
Leans Obama5959296
Weak Obama161616312
Weak Romney161616226
Leans Romney44210
Strong Romney162206
Safe Romney44

This table summarizes results by state. Click on the poll count to see the individual polls included for the state.

00EC#Total%%ObamaRomney
84VotespollsVotesObamaRomney% wins% wins
AL91*558 36.6 63.4 0.0100.0
AK30*(0)(100)
AZ111*775 44.1 55.9 0.9 99.1
AR61*679 36.8 63.2 0.0100.0
CA551*780 59.7 40.3100.0 0.0
CO953612 50.4 49.6 61.3 38.7
CT732716 54.7 45.3100.0 0.0
DE30(100)(0)
DC31*94 88.3 11.7100.0 0.0
FL2965117 48.2 51.8 3.5 96.5
GA1622129 47.0 53.0 2.3 97.7
HI41*517 64.8 35.2100.0 0.0
ID40*(0)(100)
IL201*546 61.5 38.5100.0 0.0
IN111344 40.7 59.3 0.7 99.3
IA621595 50.5 49.5 60.4 39.6
KS61*442 45.0 55.0 7.3 92.7
KY81*528 45.5 54.5 6.9 93.2
LA81*542 41.1 58.9 0.1 99.9
ME21*516 58.3 41.7 99.8 0.2
ME111*488 64.8 35.2100.0 0.0
ME211*421 53.7 46.3 85.6 14.4
MD101*792 62.4 37.6100.0 0.0
MA1111048 58.5 41.5100.0 0.0
MI1644318 50.2 49.8 57.4 42.6
MN101*472 53.6 46.4 85.9 14.1
MS61*717 40.0 60.0 0.0100.0
MO1063135 47.8 52.2 4.2 95.8
MT31465 40.9 59.1 0.3 99.7
NE21*553 43.4 56.6 1.4 98.6
NE111*389 45.5 54.5 10.4 89.6
NE211*252 49.6 50.4 46.8 53.2
NE311*284 35.9 64.1 0.1 99.9
NV621606 51.3 48.7 76.9 23.1
NH421540 52.6 47.4 91.8 8.2
NJ141625 57.9 42.1 99.7 0.3
NM51450 57.8 42.2 99.0 1.0
NY291637 65.3 34.7100.0 0.0
NC1542429 49.8 50.2 44.0 56.0
ND31*348 41.4 58.6 1.2 98.8
OH1865447 51.1 48.9 87.0 13.0
OK71431 33.4 66.6 0.0100.0
OR71*631 54.4 45.6 93.8 6.2
PA2031541 54.1 45.9 99.0 1.0
RI41*495 59.4 40.6 99.9 0.1
SC91*1833 51.7 48.3 85.8 14.2
SD31*497 46.1 53.9 11.3 88.7
TN111*654 46.0 54.0 7.1 92.9
TX381*460 38.9 61.1 0.0100.0
UT61*1149 27.7 72.3 0.0100.0
VT31415 71.3 28.7100.0 0.0
VA1364110 51.4 48.6 90.0 10.0
WA121477 59.3 40.7 99.8 0.2
WV51*373 40.8 59.2 0.5 99.5
WI1076975 51.7 48.3 97.9 2.1
WY30(0)(100)

* An older poll was used (i.e. no recent polls exist).

Details of the methods are given in the FAQ.

The most recent analysis in this match-up can be found from this page.

Comments

  1. 1

    Michael spews:

    Obama takes the latest Colorado poll by +4% over Romney, and he leads in four of the five current polls for the state.

    Been tellin’ ya’ that Colorado was going to go blue.

    Nice to see that Obama has a fighting chance in missouri, but I still think that Romney’s going to win that one.

  2. 2

    Politically Incorrect spews:

    Like I said before, people will vote for whomever promises to keep their particular gravy train running on schedule.

  3. 3

    Richard Pope spews:

    Still need to take care of South Carolina. A reasonable poll result for that state should produce about 243 to 244 mean electoral votes for Romney, and at least a 5% to 7% chance of winning overall.

  4. 4

    Roger Rabbit spews:

    We’re in the middle of the GOP convention, so this is probably the high water mark for Romney and the peanut-throwing party. Obama’s numbers will strengthen after the Democratic convention and the debates.

  5. 5

    Michael spews:

    I watched Rob Portman’s convention speech, total snoozer. I must not have been the only one that though so as there was plenty of open space in the area.

    I thought Rick Santorum did pretty well last night

  6. 7

    Serial Conservative spews:

    Darryl, do you have any comments about the Columbus Dispatch poll in OH, which was a mail poll? Thanks in advance.

  7. 8

    Serial Conservative spews:

    @ 4

    We’re in the middle of the GOP convention, so this is probably the high water mark for Romney

    The most recent poll is dated 8/26 and the convention started on the 28th.

    Assuming some post-convention bounce, Romney/Ryan will poll better in the next series than they did in the last one.

    Next week you’ll be telling us it’s the high water mark for Romney. Two weeks after that, the same thing.

    Yada yada yada.

  8. 10

    Serial Conservative spews:

    @ 9

    That got plenty of press when it came out well over a week ago. Off-topic tonite. Although I just heard Maddow question Scott Walker about it.

  9. 11

    spews:

    Richard Pope @ 3,

    “Still need to take care of South Carolina.”

    Yep. Still no new poll there.

    “A reasonable poll result for that state should produce about 243 to 244 mean electoral votes for Romney, and at least a 5% to 7% chance of winning overall.”

    Could be. But your hunch about how SC goes isn’t much to go on, is it?

  10. 12

    spews:

    Serial Conservative,

    “Darryl, do you have any comments about the Columbus Dispatch poll in OH, which was a mail poll? Thanks in advance.”

    Not really. Mail-in polls are unusual, but provided the sample selection methods are carefully done, there is no reason to exclude them. And their track record with this poll is pretty good.

    For example, in 2008 they had a poll with 2,164 responses taken from 22-OCT to 31-OCT and found 46% McCain, 52% Obama. The actual election result in Ohio was 46.9% McCain, 51.5% Obama. Not too shabby!

  11. 13

    spews:

    Serial Conservative,

    “Assuming some post-convention bounce, Romney/Ryan will poll better in the next series than they did in the last one.”

    Yep…there will almost certainly be better results for Romney over the next three or four weeks. After that…who knows! In 2008, the Palin + convention bounce lasted one month, but once Obama regained parity with his convention maximum, it was down hill for McCain thereafter.

    Of course, the dynamics of that race are pretty different from this one, including the fact that there was no incumbent, the Dem. convention happened first, and then there was that public vetting of Sarah Palin thing….

  12. 14

    Serial Conservative spews:

    @ 13

    No disagreement with any of what you said. My point @ 8 was to refute a short-sighted @ 4 comment about where Romney is likely to peak. I’m confident it has not yet happened.

  13. 15

    spews:

    Serial Conservative,

    “No disagreement with any of what you said. My point @ 8 was to refute a short-sighted @ 4 comment about where Romney is likely to peak. I’m confident it has not yet happened.”

    I understand. I was agreeing with you and backing up what you said!

  14. 16

    Richard Pope spews:

    I assume if the GOP ticket improves their personal likeability, there will be a measurable convention bounce. Romney trails Obama by more than 2-to-1 in polling measuring which candidate voters like best. So if Romney polls roughly even with Obama, in spite of being mostly disliked, a good PR package this week could help him a lot.

    So the GOP convention certainly looks like a decent PR package at least … Not much substance, not much truth, but sure looks good on the surface …

  15. 17

    Roger Rabbit spews:

    @10 And you’re going to hear a lot more about Ryan’s dishonesty in blaming Obama for an auto plant closing in 2008.

    Blame Obama! Blame Obama! Blame Obama!

    That’s the entire GOP platform in 6 words.

  16. 21

    Red spews:

    These are primarily Democrat-sponsored polls. Take a look at RealClearPolitics poll of polls comparing President Obama today with President Bush on 8/30/04.
    http://www.realclearpolitics.c.....roval.html

    I understand it’s based on National Polls, but there is a 4 % point difference. President Obama is at 47.6% Approval and 48.7% Disapproval or a Negative 1.1% whereas President Bush was at 49.5% Approval and 46.7% Disapproval or a Positive 2.8%. That is quite a difference for an incumbent at the same point in time. And we all know how close that election turned out to be, with undecided voters breaking clearly Against the Incumbent. It will likely happen again.
    It’s important when looking at these types of analysis to take a giant step back and a big whiff to see the bullshit factor of trying to use stats to sway opinion. It is happening by both sides all over the Blogosphere.
    The other thing to note is that this Blog’s analysis doesn’t include the Convention bounce and little of the Ryan impact. At some point, old dated polls ought to be eliminated. They are meaningless.

  17. 22

    Serial conservative spews:

    @ 21

    Interesting you bring up 2004.

    Read this earlier this morning:

    Democratic Party Poll: Gallup Sees Rise In Unfavorable Rating

    For the first time ever, the Democratic favorability ratio, which has always been within the range of 1.20 to 1.56, is now below 1. It is a stunningly low .83, which is 31% lower than the prior Democratic Party low of 1.20, which was reached in 2004. . .

    http://www.huffingtonpost.com/.....40776.html

  18. 23

    Red spews:

    17. Roger Rabbit spews:

    Blame Obama! Blame Obama! Blame Obama!

    That’s the entire GOP platform in 6 words.

    Worked well for the Democrats in 2008, all they did was substitute Obama for Bush. Paul Ryan ripped Obama apart last night and highlighted policy issues and President Obama’s decisions and inaction. My guess is you will see about $600 Million going to drumbeat that message thru Election Day. President Obama will drain the Democrat coffers leaving all other Democrat candidates high & dry and still only have 1/2 of that to defend himself.
    I suspect this will get real interesting.
    Paul Ryan has pointed out President Obama’s propensity to mistake speeches for real leadership. Paul Ryan is everything Mitt Romney is not. They are a great team. President Obama is out there all by himself with an incompetent VP Joe Biden throwing up all over himself every time he turns around.

  19. 25

    Red spews:

    @24-
    So what. You are looking at old odds. Things are about to drastically change. I doubt you could even get those odds today 8/30/12, but if you can, grab Romney/Ryan.

    You saw what happened with the Internet Poker scandals, didn’t you? Hundreds of millions scammed by big poker star names.

  20. 27

    Rael spews:

    @24
    @25
    @26
    Slightly off-topic, but since we are talking odds … still waiting to hear from Serial Conservative on our $1k even-money bet on the Presidential election.

    Can’t say I blame him for stalling.
    Taking Romney at even-money is a sucker bet.

    Apparently it is too much to ask that he just be honest & come out & say he’s not taking that sucker bet.

  21. 28

    spews:

    Mr. NOT Cynical @ 21

    “These are primarily Democrat-sponsored polls.”

    No they’re not.

    “Take a look at RealClearPolitics poll of polls comparing President Obama today with President Bush on 8/30/04.”

    But, but, but, but, Mr. NOT Cynical, we don’t elect Presidents by their approval rating. And we don’t elect them by popular vote either. We elect them state by state using the electoral college.

    “I understand it’s based on National Polls, but there is a 4 % point difference.”

    Bullshit. If you look at the RCP average between Feb and now, Bush and Obama has swapped popularity “leads” numerous times.

    “And we all know how close that election turned out to be, with undecided voters breaking clearly Against the Incumbent. It will likely happen again.”

    Of course, the state head-to-head polls also suggested a very close election. They are not doing so right now.

    “It’s important when looking at these types of analysis to take a giant step back and a big whiff to see the bullshit factor of trying to use stats to sway opinion.”

    Except that my poll analyses don’t push a particular viewpoint except, “who is in the lead based on the state head-to-head polls”.

    “It is happening by both sides all over the Blogosphere.”

    Maybe…but not in my analyses. Anyone who understands basic probability theory can replicate my analyses and get the same results that I get.

    “The other thing to note is that this Blog’s analysis doesn’t include the Convention bounce and little of the Ryan impact.”

    You are pathetically stupid. As of yesterday, none of the polls taken since the convention began have been released yet.

    Second, the titles of my last three poll analyses have specifically mentioned the Ryan Bump. Do you know how to fucking read?

    “At some point, old dated polls ought to be eliminated. They are meaningless.”

    The old polls are removed from analysis according to a well-defined algorithm. Read the FAQ and quit embarrassing yourself.

  22. 30

    Red spews:

    2 new State Polls today–
    President Obama up 3% in Michigan and Mitt Romney up 13% in Missouri
    Mr. Darryl is kind of weird and dillusional.
    Look at all the silly poll analysis like his. On both sides. All they are trying to do is influence public opinion. A lot of work for virtually no return.

  23. 31

    Steve spews:

    “Is there anything more pathetic than a right winger suffering from dementia?”

    Yeah, a wingnut who spends too much time in the barn. I refer you to the Klown act @30.

  24. 32

    spews:

    Mr. NOT Cynical @ 30,

    “2 new State Polls today–
    President Obama up 3% in Michigan and Mitt Romney up 13% in Missouri

    Yep…they’ll both be in my next analysis.

    “Mr. Darryl is kind of weird and dillusional.”

    Umm…yeah. Projection much?

    “Look at all the silly poll analysis like his. On both sides. All they are trying to do is influence public opinion.”

    I cannot speak for the analyses of other’s but this is incorrect for my analyses, which are objective, and based on straight-forward application of probability theory.

    I understand that you have a difficult time conceiving of someone doing something without partisan purpose. But that is you, and I ain’t you.

    “A lot of work for virtually no return.”

    Wrong again. It give me satisfaction to objectively assess the state of the race.

    But…you know, Mr. NOT Cynical, if it gives you heartburn or brings you to the edge of a coronary, don’t bother reading ‘em.

    We wouldn’t want you to get hurt over a little applied probability theory, for Pete’s sake!