HorsesAss.Org

Poll Analysis: Two days of good polls for Obama

by — ,


Obama Romney
98.9% probability of winning 1.1% probability of winning
Mean of 309 electoral votes Mean of 229 electoral votes

Electoral College Map

Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Lousiana Maine Maryland Massachusettes Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia D.C. Washington West Virginia Wisconsin Wyoming

Electoral College Map

Georgia Alaska Arizona Arkansas California Colorado Delaware Connecticut Florida Mississippi Alabama Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia D.C. Washington West Virginia Wisconsin Wyoming

My previous analysis was completed early Friday morning, before most polls were released. The analysis showed President Barack Obama leading Governor Mitt Romney by 302 to 236 electoral votes (on average). In an election held yesterday, Obama would be expected to win with a 94.4% probability, and Romney with a 5.6% probability.

There have been 35 new polls released since then that cover 23 “states”. I put states in quotes, because we get polls for ME-1 and ME-2 this batch. Lots of swing states are included in this batch, and they largely come down on the side of Obama:

start end sample % % %
st poll date date size MOE O R diff
CA Field Poll 25-Oct 30-Oct 751 3.6 54 39 O+15
CO PPP 31-Oct 01-Nov 825 — 50 46 O+4
CO SurveyUSA 28-Oct 31-Oct 695 3.8 47 45 O+2
CT PPP 01-Nov 02-Nov 1220 2.8 55 42 O+13
FL Mason-Dixon 30-Oct 01-Nov 800 3.5 45 51 R+6
FL Marist 30-Oct 01-Nov 1545 2.5 49 47 O+2
GA 20/20 Insight 29-Oct 31-Oct 1316 2.7 45 52 R+7
HI Civil Beat 24-Oct 26-Oct 1218 2.8 61 34 O+27
IN Howey DePauw 28-Oct 30-Oct 800 3.5 41 51 R+10
IA Gravis Marketing 01-Nov 01-Nov 594 4.0 49 45 O+4
IA Selzer 30-Oct 02-Nov 800 3.5 47 42 O+5
IA Mellman Group 30-Oct 01-Nov 600 4.0 46 44 O+2
ME PPP 01-Nov 02-Nov 1633 2.4 55 42 O+13
ME1 PPP 01-Nov 02-Nov 817 — 59 39 O+20
ME2 Gravis 01-Nov 02-Nov 509 4.3 50 47 O+3
ME2 PPP 01-Nov 02-Nov 816 — 51 46 O+5
MA PPP 01-Nov 02-Nov 1089 3.0 57 42 O+15
MA Kimball 31-Oct 01-Nov 761 3.5 54.0 41.4 O+12.6
MI PPP 01-Nov 03-Nov 700 3.7 52 46 O+6
MI Rasmussen 01-Nov 01-Nov 750 4.0 52 47 O+5
MI Grove Insight 31-Oct 01-Nov 500 4.4 48 41 O+7
MN PPP 31-Oct 01-Nov 772 — 53 44 O+9
NE WeAskAmerica 01-Nov 01-Nov 1178 3.0 41 54 R+13
NV Mellman Group 29-Oct 31-Oct 600 4.0 50 44 O+6
NH Gravis Marketing 01-Nov 01-Nov 497 4.3 50 49 O+1
NH New England Collage 29-Oct 31-Oct 1017 3.7 49.5 44.4 O+5.1
OH Rasmussen 01-Nov 01-Nov 750 4.0 49 49 tie
OH Marist 31-Oct 01-Nov 971 3.1 51 45 O+6
OH CNN/OR 30-Oct 01-Nov 796 3.5 50 47 O+3
OH WeAskAmerica 30-Oct 01-Nov 1649 3.0 50.2 45.8 O+4.4
OR PPP 31-Oct 01-Nov 921 — 52 46 O+6
SD Neilson Brothers 28-Oct 31-Oct 634 3.9 42 50 R+8
UT Dan Jones 26-Oct 01-Nov 870 3.4 26 69 R+43
VA WeAskAmerica 30-Oct 01-Nov 1069 3.0 48.5 47.6 O+0.9
WI WeAskAmerica 30-Oct 01-Nov 1210 3.0 51.5 44.8 O+6.7

Both new Colorado polls offer Obama slim margins over Romney. With five current polls splitting 4 to 1 for Obama, the analysis gives Obama an 81% probability of taking the state.

We get one Florida poll for each candidate, but Romney gets the net benefit. The current polls split 3 to 2 in favor of Romney, giving the G.O.P. nominee about 2/3 probability of taking the state.

All three new Iowa polls go to Obama, who also takes 6 of 7 current polls.

Maine-2 was considered a swing “state”, but both new polls go to Obama. Together the suggest Obama has a 87% chance of taking ME-2’s single electoral vote.

Three new Michigan polls give modest leads to Obama. The President takes all five current polls, suggesting a very high probability of taking the state.

The new Minnesota poll is pretty solid for Obama, who ends up with a high probability of winning the state.

The new Nevada poll puts Obama over Romney by a modest +6%. As it happens, that’s the only poll that falls in the current poll window. It suggests Obama would win the state now with a 86% probability.

Obama leads in two new New Hampshire polls. One gives Obama a slim +1% and the other gives him a +5.1%. All four current polls go to Obama and he looks to have an 88% probability of taking the state now.

Four of five new Ohio polls go to Obama, the fifth is a tie. We now have eleven polls taken in the past week, and Obama leads in nine; Romney leads in one. If the election was held now, Obama would take the state with a 97% probabililty.

In Virginia, Obama squeaks out a +0.9% lead. It is the only current poll, so Obama comes away with a 58% probability of winning, based on this evidence.

Obama gets a modest +6.7% in the new Wisconsin poll. Now he leads in four of five current polls, with the fifth poll being a tie. In the analysis, Obama won just under 100% of the simulated elections.

After 100,000 simulated elections, Obama wins 98,915 times and Romney wins 1,085 times (including the 66 ties). Obama received (on average) 309 (+7) to Romney’s 229 (-7) electoral votes. In an election held now, Obama would have a 98.9% (+4.5%) probability of winning and Romney would have a 1.1% (-4.5%) probability of winning.

The long term trends in this race can be seen from a series of elections simulated every seven days using polls from 03 Nov 2011 to 03 Nov 2012, and including polls from the preceding seven days (FAQ).

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

Ten most probable electoral vote outcomes for Obama (full distribution here):

  • 303 electoral votes with a 7.12% probability
  • 290 electoral votes with a 4.95% probability
  • 319 electoral votes with a 3.87% probability
  • 332 electoral votes with a 3.41% probability
  • 318 electoral votes with a 3.18% probability
  • 304 electoral votes with a 3.05% probability
  • 305 electoral votes with a 2.32% probability
  • 306 electoral votes with a 2.23% probability
  • 296 electoral votes with a 2.20% probability
  • 299 electoral votes with a 2.15% probability

After 100,000 simulations:

  • Obama wins 98.9%, Romney wins 1.1%.
  • Average (SE) EC votes for Obama: 308.7 (19.1)
  • Average (SE) EC votes for Romney: 229.3 (19.1)
  • Median (95% CI) EC votes for Obama: 305 (275, 347)
  • Median (95% CI) EC votes for Romney: 233 (191, 263)

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%+):

Threshold Safe + Strong + Leans + Weak
Safe Obama 78
Strong Obama 185 263
Leans Obama 27 27 290
Weak Obama 13 13 13 303
Weak Romney 0 0 0 235
Leans Romney 57 57 235
Strong Romney 125 178
Safe Romney 53

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

0 0 EC # Total % % Obama Romney
8 4 Votes polls Votes Obama Romney % wins % wins
AL 9 1* 404 39.6 60.4 0.1 99.9
AK 3 0* (0) (100)
AZ 11 1* 480 45.8 54.2 10.2 89.8
AR 6 1* 571 34.9 65.1 0.0 100.0
CA 55 1 699 58.1 41.9 99.8 0.2
CO 9 5 4114 51.0 49.0 80.8 19.2
CT 7 1 1183 56.7 43.3 99.9 0.1
DE 3 0 (100) (0)
DC 3 1* 1173 91.6 8.4 100.0 0.0
FL 29 5 4581 49.6 50.4 35.0 65.0
GA 16 1 1276 46.4 53.6 3.3 96.7
HI 4 1* 1157 64.2 35.8 100.0 0.0
ID 4 1* 563 30.0 70.0 0.0 100.0
IL 20 1 1174 58.2 41.8 100.0 0.0
IN 11 2 1471 43.9 56.1 0.1 99.9
IA 6 7 5381 51.8 48.2 97.0 3.0
KS 6 2* 1143 39.4 60.6 0.0 100.0
KY 8 1* 557 42.4 57.6 0.7 99.3
LA 8 1* 2548 37.9 62.1 0.0 100.0
ME 2 1 1584 56.7 43.3 100.0 0.0
ME1 1 1 801 60.2 39.8 100.0 0.0
ME2 1 2 1284 52.2 47.8 86.6 13.4
MD 10 2* 1538 61.6 38.4 100.0 0.0
MA 11 2 1804 57.2 42.8 100.0 0.0
MI 16 5 2969 52.8 47.2 98.4 1.6
MN 10 2 1283 54.2 45.8 98.6 1.4
MS 6 1* 717 40.0 60.0 0.0 100.0
MO 10 1 1169 44.0 56.0 0.2 99.8
MT 3 1 744 45.8 54.2 5.4 94.6
NE 2 3 3024 40.8 59.2 0.0 100.0
NE1 1 1* 389 45.5 54.5 10.0 90.0
NE2 1 1* 646 47.4 52.6 17.3 82.7
NE3 1 1* 284 35.9 64.1 0.0 100.0
NV 6 1 564 53.2 46.8 86.1 13.9
NH 4 4 3258 51.4 48.6 88.2 11.8
NJ 14 5* 3773 55.6 44.4 100.0 0.0
NM 5 2* 1307 54.8 45.2 99.4 0.6
NY 29 3* 1770 63.8 36.2 100.0 0.0
NC 15 2 1313 48.8 51.2 27.0 73.0
ND 3 2 1283 41.6 58.4 0.0 100.0
OH 18 11 9152 51.5 48.5 97.2 2.8
OK 7 1* 279 35.8 64.2 0.1 99.9
OR 7 1 903 53.0 47.0 89.4 10.6
PA 20 10* 7146 51.5 48.5 96.8 3.2
RI 4 1* 523 62.1 37.9 100.0 0.0
SC 9 3* 4199 48.2 51.8 4.8 95.2
SD 3 1 583 45.6 54.4 6.5 93.5
TN 11 1* 566 36.6 63.4 0.0 100.0
TX 38 1* 752 41.5 58.5 0.0 100.0
UT 6 1 826 27.4 72.6 0.0 100.0
VT 3 1* 415 71.3 28.7 100.0 0.0
VA 13 1 1027 50.4 49.6 57.7 42.3
WA 12 1 522 57.5 42.5 98.9 1.1
WV 5 1* 361 42.1 57.9 1.8 98.2
WI 10 5 4704 52.7 47.3 99.6 0.4
WY 3 0 (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

  2. 2

    It’s starting to look like the only states Obama will lose from 2008 are North Carolina and Florida and he’s still got an outside shot at Florida.

    So much for that sound rejection Serial was talking about.

  3. 3

    Ryan,
    What happened to Obama winning Tennessee and Kentucky?

    I discussed that in the previous Poll Analysis comment thread.

  6. 6

    Bob @ 5,

    “But Romney has no momentum. Nope.”

    Almost certainly not. One tie from a pollster that has produced bizarre “outliers” in PA shouldn’t be taken too seriously. With enough polls in the mix, those strong “house effects” tend to cancel one another. So the poll you complain about above now has its “counterweight”.

    Then again, if you click your heals three times and swallow two Magic Beans, maybe Romney will have a shot at PA afterall.

  7. 7

    In Minnesota, one point difference.

    Nope, no movement toward Romney there.

    Barack Obama and Mitt Romney are separated by just 1 point in Minnesota, effectively making the race there a toss-up, according to polling taken for the conservative American Future Fund.

    http://www.politico.com/blogs/.....48296.html

    (Not sure whether this meets the qualifications for inclusion in Darryl’s analyses. From the link:

    Romney takes 46 percent of the vote to Obama’s 45 percent in the poll, which was conducted by the GOP firm NMB Research and shared with POLITICO. The Republican presidential nominee is up 13 points among independents, ahead of Obama 49 percent to 36 percent.    )

    Note that Romney takes independents by double digits.

    Will the Dems turn out this year? It’s the only thing that will keep Romney from 300 EV.

    If only there was a way to predict based on, I don’t know, maybe early voting turnout compared with 2008 or something:

    http://www.huffingtonpost.com/.....69037.html

    COLORADO

    Who’s leading the early vote: Republicans, 38 percent to Democrats’ 35 percent.

    How significant is it: Very. Nearly 80 percent of voters voted early in 2008.

    The spin: Democrats say they are leading among “non-midterm voters” who are voting early. But there’s no getting around it: Republicans — who lost the early vote in Colorado by 4 points in 2008 — are winning it this time, and the early vote is a huge majority of the total vote in this state Obama won by 9 points in 2008.

    Who’s really winning: Republicans.

    http://www.theatlantic.com/pol.....ng/264436/

    http://boe.cuyahogacounty.us/p.....arison.pdf

    Nah. What am I thinking?

    Let’s go look at poll data up to 7 days old, with respondent D+ spreads approaching double digits.

  8. 8

    @ 6

    Was talking to my cousin in Philly last night. He tells me the hatred for Romney there is palpable. A LOT of folks know the dudes a crook and a tax evader. Philadelphia may be full of assholes, but they know a bullshit artist when they see one.

  10. 10

    @ 8

    Bet Philly is employed with lotsa unemployed types dependent on government handouts, too. Not surprising you know one or more of them, there.

    BTW. There’s a western PA, too. That’s where the work is done in that state.

  11. 11

    Take note for deadtoad’s “hatred”. My cousins are in West Philly. Goldy and I talked about that one night long ago at a DL. My cousins don’t hate Romney. They just drink the Obummer kook-aid and vote for him cuz he’s black. That’s the major reason they vote for him. When asked about the higher black unemployment rate I got static silence on the phone. Oh well… low information voters. Tax evader… Since the tax preparation house claimed Romney paid all applicable taxes.. proves deadtoad’s family are low information voters. Apparently his cousin forgot about the original federal tax on the original money made to make the investments. Now we see why deadtoad is like his cousin. Low information voter!

  12. 12

    @ 7

    Apparently the MN poll I referenced was conducted by Neil Newhouse’s firm, and he’s a Romney pollster.

    Huge grain of salt with that poll likely prudent.

    Wonder if the poll passes Darryl’s smell test.

  13. 13

    Bob,

    “I’m on a no-fly list, now?”

    Nope…the automated spam filter probably thought you had too many links or something.

  14. 14

    There’s a western PA, too. That’s where the work is done in that state.

    You just can’t not be a schmuck. You’re powerless before the overwhelming suasion of suckitude.

    Which stage of grief are you transiting now? Is that it? Is that what underlies the primal YAWP of your posts of late, overwhelming existential grief?

  15. 15

    Puddy can’t wait for Tuesday… We’ll see if all these polls are right or just a few are right. And if the HA leftist are left crying and Nate Silver and Intrade are wrong… what will the leftists do?

  18. 18

    How many 100’s of millions of dollars have Romney various right-wing pacs spent and only gotten 3 states to flip? That doesn’t sound like a good investemnt to me. It also sounds like they don’t have the support of the American people behind them.

  19. 19

    Bob @

    “Nope, no movement toward Romney there.”

    Almost certainly not. One poll cannot really show a trend. Assuming the poll is legit (i.e. not selectively released), the result easily falls within the O+7 range if you consider sampling variability for a poll of only 500 respondents.

    I’ll evaluate that poll against the inclusion criteria when I do my next sweep.

    Seriously, your obsession with individual polls, and only polls that favor your candidate borders on the absurd!

    Please try to think more like a scientist and less like a child. In other words, evaluate polls and their results replacing Romney and Obama with Candidate X and Candidate Y, and be sure you would come to the same inference if the labels were swapped….

  22. 22

    Seen any R+ 9 polls lately?

    You really are unteachable, despite Darryl’s seemingly infinite patience.

  23. 23

    Person Playing Puddybud,

    “And if the HA leftist are left crying and Nate Silver and Intrade are wrong… “

    There’s a saying that “one piece of data is worth 1,000 expert opinions.”

    Data: In 2008, Intrade, Nate Silver, and I were all pretty damn accurate!

  24. 24

    @16

    You forget that they’re also not taking into account the various polling sites (e.g. TX) where the NAACP has been given free reign to campaign INSIDE polling places.

    Maybe this is a quid pro quo: Obama tells Putin he’ll have more “flexibility” after 11/6 in exchange for Putin showing him how to better rig elections.

    BUT… If Romney wins, I think we should be sure to send Darryl’s charts and graphs to his bosses at the Dept of Anthropology at the UW. If/when they need to make cuts, this glorified TA should be the first to go.

  25. 25

    @19

    I don’t think it is childish to look at data saying most of CO has voted and the GOP is up 3 over Dems in that tally (data @7 above), then look at the polls you have listed and see 4 of 5 favor Obama, and wonder how that happens.

    Given data above, why should I believe Obama has 80+% chance of taking the state? it makes no sense, whether one is scientific or childish.

  26. 26

    To Da Perfessa,

    2008 was then this is now. These 2012 polls are swinging more than the dunceman swinging from a tree with his prehensile tail. Someone has to be wrong. So if you three are wrong what will be your response. You see Puddy remembers the polls from Wisconsin this year. Everyone except Rasmussen called it too close to call. Rasmussen had it 53/47 almost dead on at 53/46.

    It was rigged? Sure when you D+6 all the time.

  27. 27

    Bob,

    “Given data above, why should I believe Obama has 80+% chance of taking the state? it makes no sense, whether one is scientific or childish.”

    Because polling offers direct evidence. Early voting stats provides indirect evidence using a non-causal argument.

    [Update: I meant to say…the childish part is not looking at early voting stats. Rather, it grasping at any evidence you can scrape up to support your hopes and dreams. It would actually be interesting to see an analysis of early voting stats in past elections for all states that do early voting and then try to forecast outcome in the current election. There is probably a weak correlation there. But you’d have to do it with the conviction of being absolutely neutral.

  28. 28

    Those D+X polls are being swung to “discourage” Republican voters. That’s why the get out the truth message is working this year. Nate got much wrong in 2010 and so he went after Rasmussen to cover his tracks. No one except Rasmussen and Dick Morris predicted the November 2010 outcome. DUMMOCRAPTS want to forget those polls as sandra fluke(s).

  29. 29

    I expect a strong Dem turnout in most states, not because there is such love for Obama as there is hate and fear of Romney. I travel amongst many Fellow Travelers (in the old sense) and even hard-core Obama-hating communists are urging people not to vote Green or Libertarian.

    I disagree with Obama on many policy issues but he at least is still tethered to reality. Pretty sad when “not insane” is a prime reason to vote for a presidential candidate.

  30. 30

    Person Playing Puddybud,

    “These 2012 polls are swinging more than the dunceman swinging from a tree with his prehensile tail. Someone has to be wrong.”

    Huh…I haven’t seen any reality-based analyses that suggest the polling is worse this year. And now that many pollsters include cell phone sub-samples, the results will likely be better for this general election than 2008.

    “You see Puddy remembers the polls from Wisconsin this year. Everyone except Rasmussen called it too close to call. Rasmussen had it 53/47 almost dead on at 53/46.”

    What you consider evidence suffers from severe selectivity bias. An objective analysis would require looking at the polling accuracy of the many hundreds of state-wide elections held over the past year. It’s possible you’d find polls all over the place compared to the gold standard (election), but I doubt it.

  31. 31

    Person Playing Puddybud,

    “Those D+X polls are being swung to “discourage” Republican voters.”

    Bullshit.

    “That’s why the get out the truth message is working this year. Nate got much wrong in 2010 and so he went after Rasmussen to cover his tracks. No one except Rasmussen and Dick Morris predicted the November 2010 outcome. DUMMOCRAPTS want to forget those polls as sandra fluke(s).”

    Interesting. I wasn’t aware the Silver’s record was lousy in 2010. And I wasn’t aware that Dick Morris has EVER predicted ANYTHING even close to reality. (Unfortunately, I suspect you are parroting some bullshit Wingding source.)

    Finally, I seriously doubt Nate Silver “goes after” pollsters. Rasmussen would be penalized in his model according to their goodness-of-fit to actual outcomes, just like all other pollsters.

  33. 33

    Darryl, I’m interested in the mechanics of your Monte Carlo simulations. I haven’t seen it done on polling data elsewhere but it makes a lot sense. Share?

  35. 35

    Reality has a well known liberal bias, so months of polling data showing the same outcome means its “skewed”.

    In the meantime, prepare yourselves for the biggest harvest of Bitter Wingnut Tears since ObamaCare was ruled constitutional by the SCOTUS.

    Gotta go . Time to prep for today’s tsunami of GOTV here in Denver.

  36. 36

    re 34: Maybe after the election, Mitch McConnell can renew his pledge, only this time he can conspire to limit Obama to two terms.

    Republicans support and encourage government sponsored torture here, so your opposition to it under Stalin only means that you are against it when it is directed at you.

  39. 39

    Dr. Hilarius @ 33

    “Darryl, I’m interested in the mechanics of your Monte Carlo simulations. I haven’t seen it done on polling data elsewhere but it makes a lot sense. Share?”

    Sure…see the FAQ.

  41. 41

    A Republican who looks at the current polling numbers and expresses confidence about Mitt’s chances is either delusional or a liar. There is no other alternative.

  45. 45

    Two little PA tidbits not to forget:

    The Republicans took note that about 85,000 Democrats who voted in the state’s primary failed to cast a vote for Obama, an undervote that they theorize is a lack of confidence in the president’s leadership that they can build upon, particularly in the coal counties bordering Ohio, Pitman says.

    and

    Some 81,000 customers were in their seventh day with no power.

    http://www.washingtonpost.com/.....story.html

    Looks like the Dems will need that D +13 advantage some well-regarded poll gave them.

    Jus’ sayin’.

  47. 47

    Bob @ 45,

    “The Republicans took note that about 85,000 Democrats who voted in the state’s primary failed to cast a vote for Obama, an undervote that they theorize is a lack of confidence in the president’s leadership that they can build upon, particularly in the coal counties bordering Ohio, Pitman says.
    “

    Ummm, Bob, you seem particularly susceptible to right wing bullshit this week. There is always undervotes in any vote. But the polls presumably pick up (as undecided) such trends. Maybe you should just click your heals again?

    “Some 81,000 customers were in their seventh day with no power.”

    Nice…so now you right-wing nutburgers are hoping to get mother nature to assist your voter disenfranchisement efforts?!?

    “Looks like the Dems will need that D+13 advantage some well-regarded poll gave them.”

    Dude…the “D+13” complaints just make you look like an idiot. Poll composition ends up showing sampling variability as does the outcomes of other measures on a poll (like the individual races). Your lack of training in even elementary probability is a real detriment to your ability to think about and discuss these thing with some insight.

  48. 48

    @ 46

    How about you take the money you were willing to wager and donate it to Northwest Harvest instead, in Darryl’s name, in appreciation for the effort he expends on this site?

    If you’re willing to lose money on a bet, rather than potentially enriching someone else, do the right thing with it.

    Your offer to wager tells me you’re willing to put your money where your mouth is. Noted.

    My response is that you should put your money where it will do some real good.

  49. 49

    @ 47


    Nice…so now you right-wing nutburgers are hoping to get mother nature to assist your voter disenfranchisement efforts?!?

    Feel free to add it to your list of excuses if Romney prevails in one of the states affected by the storm that you currently have in Obama’s column. Don’t forget the Bradley Effect and a whole bunch of white people who suddenly realized they were racist.

    I don’t recall you admonishing the HA types cheering Obama’s opportunity to act presidential and win accolades from Christie and Bloomberg earlier this week, which was a benefit to his campaign provided by the storm. It’s not very consistent, then, for you to make an accusation of me when all I did was point out a potential Team Obama negative aspect of the storm’s damage. As this is a partisan blog, I take no offense.

    Regarding variability, sure, if the data is totally unweighted after being acquired, then it’s natural variability. But polls are weighted frequently to compensate for some aspect of the sampled population that doesn’t match the (in this case) state in which the sample we collected. I think it was We Ask America that gave a paragraph stating how hard they worked this week with their data weighting to derive what they felt was appropriate.

    I bring up D + 13 because it’s so far removed from what happened in PA in 2008 and in 2010. If it’s a natural poll result then their likely voter screen sucks because it ends up looking like a registered voter poll based on data in that state. It’s also not the first time it’s happened – we talked about it in May, I recall.

    I guess what I am getting at is polls can be, and have been, wrong. In 2010 the RCP average picked Buck to win in CO. He didn’t. If I recall correctly the RCP average had Reid losing in 2010 and he didn’t. I think the poll average was wrong in the Alaska 2010 Senate race as well although that was a three-way and very weird so that really shouldn’t be part of this discussion.

    If – and I really don’t know although I’m optimistic – Romney wins on Tuesday, unless you and Nate do some major revisions based on final polls before then, your methodology will have misled you pretty badly, and you will naturally begin to look for the reasons that happened.

    I think that, should that occur, one of the reasons you come up with will be poll weighting this election season that too often does not reflect reality when the D/R/I is compared with 2008 and 2010 exit data.

    In 2010, PA elected a governor and a US Senator from the Republican party, despite a double-digit registration advantage favoring Democrats in the state.

    D + 13 in that state is a joke.

    Call me childish, call me uneducated, call me an idiot. Do whatever you feel you need to do if you feel your methods are being attacked.

    I’ll be pleased to offer a full mea culpa Wednesday morning, should Obama prevail.

    Thank you for doing all of this.

  50. 50

    45. Serial Conservative spews:
    Two little PA tidbits not to forget:

    Nate Silver says Romney’s play for PA is basically a Hail Mary … he might as well try it because he doesn’t have any better options.

  51. 51

    @50 Cereal Bob, like a good little appartchik, is following the R’s marching orders of trying to create a “Romney momentum” by pretending there is one. This is very characteristic of R’s as they believe saying something makes it true.

  52. 52

    @24: “BUT… If Romney wins, I think we should be sure to send Darryl’s charts and graphs to his bosses at the Dept of Anthropology at the UW. If/when they need to make cuts, this glorified TA should be the first to go.”
    What a world-class prick. You have no evidence that Darryl is doing this work during his paid time, and yet you would have no problem fucking with his employment–just because you don’t like what the numbers show.
    You really are an asshole.

  55. 55

    Thank the Great Mother Rabbit Spirit we won’t have to read Cereal Bob’s self-deluding cheerleading much longer.

  57. 57

    Nate Silver Update

    One of the Gopers’ favorite props for rationalizing a Romney win is fast disappearing: Obama is opening up a gap in the national polls that until now showed a tied race.

    “As of this writing, on Sunday evening, Mr. Obama led by an average of 1.3 percentage points across 12 national polls that had been published over the course of the prior 24 hours … there is enough data to conclude that Mr. Obama probably has a slight edge from national surveys, which until recently had pointed toward a tie or perhaps a modest advantage for Mr. Romney ….”

    As for Romney’s purported momentum, “We’ve observed the race shifting toward [Obama] over the past two to three weeks ….”

    http://fivethirtyeight.blogs.n.....alignment/

    Roger Rabbit Commentary: RealClearPolitics also has Obama ahead of Romney in national polls, 47.9% to 47.4%, which is a change from recent RCP figures that had the candidates tied or Romney slightly ahead. There’s no question a shift is taking place in voter sentiment. It’s just not in the direction Romney boosters claim it is.

  58. 58

    RCP’s electoral map with no tossups gives Obama 303 EVs to Romney’s 235; and awards Ohio, Virginia, Wisconsin, Colorado, Iowa, Nevada, and New Hampshire to Obama with the only swing states going to Romney being Florida and North Carolina.

    Of course, polls can be wrong, for several reasons: (a) People may be lying to pollsters, (b) the polling methodology may be flawed, (c) pollsters may misinterpret data, (d) polls don’t reflect the impact of external events on turnout (e.g., Hurricane Sandy, GOP voter suppression efforts, etc.), (e) pollsters may be biased, (f) voters may change their minds in the voting booth, and so on.

    But given the broad agreement of various polls that Obama is on his way to re-election, Nate Silver was correct when he said yesterday that Romney’s only chance of winning now is if the polls are wrong, because with one day to go before Election Day the polls certainly don’t give his supporters much reason for hope.

  59. 59

    RCP now projects the Senate remaining unchanged at 53 D’s to 47 R’s. If that’s how it plays out, the R’s will get nothing for all the time, effort, and money they’ve poured into this year’s Senate races.

    In fact, RCP’s predicted 3 pickups for each party masks a setback for the R’s. They will gain seats in the relatively inconsequential states of Montana, North Dakota, and Nebraska, but are facing more important losses in Massachusetts and Wisconsin, and an embarrassing loss in solid-red Indiana.

  60. 60

    You know what I cannot understand? It is how ordinary Republican people, the regular citizens with rightward preferences, so quick to wrap themselves in the flag, to accuse others of destroying America, to decorate their ads with gaudy war eagles, to consider the Constitution a gift from ‘God’ – how is it that all these ‘patriots’ are so perfectly comfortable with the systematic, relentless, unforgiving, fascistic destruction of other peoples’ access to the ballot. The Republican Party’s war on voting by brown and black and poor people – people they suspect of the crime of voting Democratic – is a profanity against democracy and represent an acquiescence to evil by the good people who think of themselves as the ‘Party of Lincoln’.

Can’t Bring Yourself to Type the Word “Ass”?

Eager to share our brilliant political commentary and blunt media criticism, but too genteel to link to horsesass.org? Well, good news, ladies: we also answer to HASeattle.com, because, you know, whatever. You're welcome!

Follow Goldy

[iire_social_icons]

HA Commenting Policy

It may be hard to believe from the vile nature of the threads, but yes, we have a commenting policy. Comments containing libel, copyright violations, spam, blatant sock puppetry, and deliberate off-topic trolling are all strictly prohibited, and may be deleted on an entirely arbitrary, sporadic, and selective basis. And repeat offenders may be banned! This is my blog. Life isn’t fair.