by Darryl, 09/30/2012, 7:23 PM
Obama Romney
100.0% probability of winning 0.0% probability of winning
Mean of 344 electoral votes Mean of 194 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

Even Newer Update: There is a real North Dakota poll that has just been released. It shows Romney leading in N.D. by 51% to 39%. The poll fails my inclusion criteria because it was conducted on behalf of the North Dakota Democratic-NPL State Party. But there you have it.

Newer Update: Okay…stuff should be fixed now.

Update: OOPS! As was pointed out in the comment thread, I accidentally “invented” a new poll that turned N.D. blue! Alas, it was an Ohio poll that got entered for the wrong state (and then entered again for Ohio). I’ll do a new analysis soon.

The analysis a few days ago showed President Barack Obama leading Governor Mitt Romney by, on average, 345 to 193 electoral votes. Since then, we’ve had a plethora of new polls released, and the result is a small gain for Obama Romney.

Here are the new polls:

start end sample % % %
st poll date date size MOE O R diff
AZ Moore 25-Sep 26-Sep 500 4.0 42 46 R+4
IA Iowa Poll 23-Sep 26-Sep 650 3.8 49 45 O+4
IA VCR 23-Sep 25-Sep 500 4.4 46 47 R+1
ME Rasmussen 25-Sep 25-Sep 500 4.5 52 40 O+12
MA Boston Globe 21-Sep 27-Sep 502 4.4 57 30 O+27
MI Gravis Marketing 21-Sep 22-Sep 804 3.3 50.0 46.2 O+3.8
MI PPP 17-Sep 19-Sep 2386 2.0 51 42 O+9
NV Marist 23-Sep 25-Sep 984 3.1 49 47 O+2
NH ARG 25-Sep 27-Sep 600 4.0 50 45 O+5
NH Marist 23-Sep 25-Sep 1012 3.1 51 44 O+7
NM PPP 17-Sep 20-Sep 3111 1.8 52 43 O+9
NC Marist 23-Sep 25-Sep 1035 3.1 48 46 O+2
OH Columbus Dispatch 19-Sep 29-Sep 1662 2.2 51 42 O+9
OH PPP 14-Sep 18-Sep 2890 1.8 50 44 O+6
PA Muhlenberg 22-Sep 26-Sep 427 5.0 49 42 O+7
PA PPP 17-Sep 18-Sep 2051 2.2 52 40 O+12
VA ARG 24-Sep 27-Sep 600 4.0 49 47 O+2
VA Suffolk 24-Sep 26-Sep 600 4.0 45.7 44.0 O+1.7
VA PPP 17-Sep 19-Sep 2770 1.9 49 43 O+6
WA Rasmussen 26-Sep 26-Sep 500 4.5 52 41 O+11

Romney continues to out poll Obama in Arizona. The three current polls, taken together, has Romney with a 95% probability of winning the state.

In Iowa, Obama leads by +4% in one poll and trails by -1% in another. Still, there are six Iowa polls taken in the past three weeks—Obama leads in four. Together they put Obama’s probability of taking the state (now) at 98%. Here is the last three months of polling:

ObamaRomney30Aug12-30Sep12Iowa

Maine has Obama leading by +12% in the new poll. There is also a newly released Critical Insights poll that is a couple weeks old and has Obama up by +16. I didn’t see the poll until after the analyses were running; it’ll be included in subsequent analyses.

Obama hangs on to a small +3.8% in one new Michigan poll. Even so, Obama pulls over 50%. Another huge, but somewhat older, Michigan poll has Obama up by +9. With Obama leading in all eight current polls, by double digits in three of them, Obama is looking unbeatable in this state.

In Nevada, Obama’s lead is just +2% in the current poll. Romney hasn’t won any of the six current polls, and Obama would be expected to win the state now with a 95% probability.

Two new New Hampshire polls have Obama up by +5% and +7%. These are Obama’s strongest showing, now giving him three of the four current polls. Romney’s chances in the state have shrunk to about 10%.

Another North Carolina poll goes Obama’s way, but by only a +2% edge. Obama now has a streak of four consecutive polls in his favor, and he takes four of the five current polls for the state. Here is what the last three months of polling look like graphically:

ObamaRomney30Aug12-30Sep12North Carolina

Two more Ohio polls go to Obama, who leads in all 12 of the polls taken over the past three weeks. In 2008, Obama won Ohio by +4.6%. If the election was held now, we’d expect Obama to win by more than a +6% margin! Here’s the recent trend:
ObamaRomney30Aug12-30Sep12Ohio

Pennsylvania shows, once again, that it isn’t a swing state. Obama’s +7% and +12% in the new polls fall in line with the rest of the ten current polls.

In Virginia, Obama has a puny +2% lead in two polls and a +6% lead in another. These polls make eleven taken in the past three weeks and Obama leads in every one of them. The analysis suggests Obama would win the hypothetical election now with certainty, even if by a smallish margin. The polling trend makes this apparent:

ObamaRomney30Aug12-30Sep12Virginia

Last, but not least, we get a new Rasmussen poll in Washington, where Obama leads Romney by a solid +11%, and takes 52% of the vote. All three current polls are double digit leads for Obama…this new poll is the smallest lead.

Now, after a Monte Carlo analysis using 100,000 simulated elections, Obama receives (on average) 347 (+2) 344 (-1) to Romney’s 191 (-2) 194 (+1) electoral votes. Obama won all 100,000 of the simulated elections, suggesting he would certainly win a hypothetical election held now.

We can view the long term trend of this race from a series of elections simulated every seven days using polls from 30 Sep 2011 to 30 Sep 2012, and including polls from the preceding 21 days (FAQ).

Looking at the media electoral vote line (purple), we see that Obama’s position is stronger than at any time in the past year tied with his strongest position over the past year (median of 347 electoral votes).

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

The most likely result from an election held now is either 350 or 351 347 or 348 electoral votes. The total fall a little short of the 365 electoral votes Obama received in 2008, but the graph shows that even 365 electoral votes isn’t entirely unattainable. On the other hand, Obama is exceedingly unlikely to receive under 300 electoral votes (as always, this refers to a hypothetical election held now).

Ten most probable electoral vote outcomes for Obama:

  • 347 electoral votes with a 17.34% probability
  • 348 electoral votes with a 16.49% probability
  • 332 electoral votes with a 6.39% probability
  • 333 electoral votes with a 6.02% probability
  • 358 electoral votes with a 4.89% probability
  • 343 electoral votes with a 3.89% probability
  • 357 electoral votes with a 3.68% probability
  • 346 electoral votes with a 2.81% probability
  • 344 electoral votes with a 2.63% probability
  • 342 electoral votes with a 2.63% probability

After 100,000 simulations:

  • Obama wins 100.0%, Romney wins 0.0%.
  • Average (SE) EC votes for Obama: 344.4 (10.0)
  • Average (SE) EC votes for Romney: 193.6 (10.0)
  • Median (95% CI) EC votes for Obama: 347 (324, 360)
  • Median (95% CI) EC votes for Romney: 191 (178, 214)

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 243
Strong Obama 88 331
Leans Obama 16 16 347
Weak Obama 1 1 1 348
Weak Romney 0 0 0 190
Leans Romney 10 10 190
Strong Romney 107 180
Safe Romney 73

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 0.2 99.8
AK 3 0* (0) (100)
AZ 11 3 1468 47.0 53.0 5.0 95.0
AR 6 1 2006 38.3 61.7 0.0 100.0
CA 55 3 2219 60.6 39.4 100.0 0.0
CO 9 9 6613 51.6 48.4 96.4 3.6
CT 7 2 1193 58.8 41.2 100.0 0.0
DE 3 0 (100) (0)
DC 3 1* 94 88.3 11.7 100.0 0.0
FL 29 14 11204 51.4 48.6 98.4 1.6
GA 16 1 439 38.5 61.5 0.0 100.0
HI 4 1* 517 64.8 35.2 100.0 0.0
ID 4 0* (0) (100)
IL 20 2* 2277 58.8 41.2 100.0 0.0
IN 11 1 736 43.5 56.5 0.5 99.5
IA 6 6 3643 52.4 47.6 97.9 2.1
KS 6 2* 1143 39.4 60.6 0.0 100.0
KY 8 1 557 42.4 57.6 0.4 99.6
LA 8 1* 542 41.1 58.9 0.1 99.9
ME 2 4 2536 58.4 41.6 100.0 0.0
ME1 1 1 412 63.3 36.7 100.0 0.0
ME2 1 1 364 53.8 46.2 84.4 15.6
MD 10 1 740 60.4 39.6 100.0 0.0
MA 11 7 3680 62.5 37.5 100.0 0.0
MI 16 8 6809 54.1 45.9 100.0 0.0
MN 10 2 1487 54.1 45.9 98.7 1.3
MS 6 1* 717 40.0 60.0 0.0 100.0
MO 10 2 1237 47.5 52.5 10.1 89.9
MT 3 2 1204 46.3 53.7 3.5 96.5
NE 2 1 728 44.0 56.0 1.1 98.9
NE1 1 1* 389 45.5 54.5 9.8 90.2
NE2 1 1 352 50.0 50.0 50.2 49.8
NE3 1 1* 284 35.9 64.1 0.1 99.9
NV 6 6 3614 51.9 48.1 95.6 4.4
NH 4 4 2436 51.8 48.2 90.7 9.3
NJ 14 3 1709 58.0 42.0 100.0 0.0
NM 5 1 2956 54.7 45.3 100.0 0.0
NY 29 1* 1426 64.6 35.4 100.0 0.0
NC 15 5 2993 50.8 49.2 72.5 27.5
ND 3 1* 348 41.4 58.6 1.1 98.9
OH 18 12 11436 53.2 46.8 100.0 0.0
OK 7 1* 431 33.4 66.6 0.0 100.0
OR 7 1 499 54.9 45.1 93.9 6.1
PA 20 10 7621 55.0 45.0 100.0 0.0
RI 4 1* 495 59.4 40.6 99.9 0.1
SC 9 3* 4199 48.2 51.8 4.8 95.2
SD 3 1* 474 41.8 58.2 0.6 99.4
TN 11 1* 654 46.0 54.0 7.6 92.4
TX 38 1 950 42.1 57.9 0.0 100.0
UT 6 1* 1149 27.7 72.3 0.0 100.0
VT 3 1* 415 71.3 28.7 100.0 0.0
VA 13 11 10928 52.5 47.5 100.0 0.0
WA 12 3 1420 58.3 41.7 100.0 0.0
WV 5 1* 361 42.1 57.9 1.8 98.2
WI 10 6 5360 54.1 45.9 100.0 0.0
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.

16 Responses to “Poll Analysis: Obama Romney gains a bit”

1. eponymous coward spews:

Obama wins North Dakota? Riiiiiiiiight…

2. Darryl spews:

Coward @ 1,

Oops! There was a copy of the Ohio poll (with Obama leading 49 to 42) pasted into N.D.!

Thanks for pointing it out.

3. Richard Pope spews:

So with North Dakota (3 EV) back into the Romney column, it should come out around 196 to 197 EV for Romney (up from 195 EV in your last analysis).

Are you going to be changing the headline to: “Poll analysis: Romney gains a bit”?

4. Meme1 spews:

Cue all the teabagging BS about “oversampling” and evil conspiracies designed to turn the tide of the election.

5. proud leftist spews:

As the Nitty Gritty Dirt Band sang years ago, “Piss on the fire, call in the dogs, and head it on back to Bowlegs.” That’s what the Mittster needs to be planning for.

6. Darryl spews:

Richard @ 3,
Yep…that’s what I did.

7. Rael spews:

Conservative trolls:

Romney is doomed.

You know it.

Give up.

8. Politically Incorrect - free minds, free markets, free people spews:

It won’t be so bad should the Milk Chocolate Messiah win in November. The House will be held by the Republicans, and they will gain in the Senate, too. Not much will happen between January 2013 and January 2017, but the Republicans will win in 2017 just because the electorate will be tired of the Democrats by then. The re-election of Obama also means the end of Hillary’s political career, and that’s a good thing, too.

9. proud leftist spews:

PI,
Do you really think divided/crippled government is a good thing at this time? Really? A government that cannot make decisions, at all, because of partisan divide? And, why in 2016 would the electorate be sick of Democrats when, according to your scenario, the Republicans would have been holding Congress? Actually, I think the Rs are headed for internecine warfare after this election. Romney will lose, and the righties will proclaim that the party needs to move ever farther to the right to win a national election. That party cannot move farther to the right. Implosion will occur. The world is moving to the left. This country needs to move that way, too.

10. proud leftist spews:

I forgot to say that the movement of history of Western Civilization has always been to the left. It is undeniable.

11. Richard Pope spews:

Darryl @ 6

You must have rerun all 50 states (and DC) with 100,000 elections, instead of just running North Dakota 100,000 times. Flipping North Dakota would, on average, change the EV totals by almost 6 for each candidate. But Romney’s total moved from only 191 EV with ND being blue to only 193 EV with ND being red.

I take it that running several 100,000 election simulations with the same data will result in the average EV totals varying by several EV’s (like maybe 2 to 5 EV’s) in each simulation?

Does it require a lot of computer time to run these things nowadays? A lot of your own time?

12. rhp6033 spews:

And… still no current S. Carolina polls!

Are pollsters so convinced that Romney would win S. Carolina that it’s not even worth polling there?

13. rhp6033 spews:

I talked to my sister in Pennsylvania over the weekend. She said they were bombarded by ads over the summer, but now the only political ads are local ones. Looks pretty clear that Romney isn’t going to be investing any more there, for him it’s a lost cause.

But if he doesn’t have a chance in Pennsylvania, then he’s really got to run the board of the other “battleground” states. And it’s not looking so good for him right now.

News today says that he has been practicing reciting “zingers” for his debate. He hopes to repeat Ronald Reagan’s peformance against Mondale, or Benson’s performance against Quale. I can’t imagine what he has in mind.

14. Darryl spews:

Richard,

“You must have rerun all 50 states (and DC) with 100,000 elections, instead of just running North Dakota 100,000 times.”

I did run the whole thing again. That is much easier than trying to hand-update each piece (rebuild the maps, all the tables, etc.).

“Flipping North Dakota would, on average, change the EV totals by almost 6 for each candidate.”

Only if the state flipped from 100% for one candidate to 100% for the other candidate.

“But Romney’s total moved from only 191 EV with ND being blue to only 193 EV with ND being red.”

If you have a cached copy of the pre-revised web page in your browser, you can see where the differences are in the long state table.

“I take it that running several 100,000 election simulations with the same data will result in the average EV totals varying by several EV’s (like maybe 2 to 5 EV’s) in each simulation?”

Yes. There is “sampling error” from only running 100,000 simulations. The EVs rarely change by more than 2 from the tests I’ve run. Essentially, the more 50-50 states there are, the more differences between simulations. This follows from the fact that the variance of a binomial process is greatest, for a fixed sample size, at p=0.5. And I am incorporating two sources of binomial variability: (1) from each original poll (that is, each simulated election, I draw a new p from the sampling distribution based on the sample size of the state’s polls) and (2) variability from the simulated voting of a sample.

BTW: That there is sampling error from only doing 100,000 simulations is why I run a million simulations for single races, like the Inslee—McKenna analyses.

“Does it require a lot of computer time to run these things nowadays? A lot of your own time?”

A single run of 100,000 elections requires roughly 5 minutes. When I do the time graph for the first time (say, after changing the “current poll” window) multiply that by 53 for the first seven days. But once I’ve done each day of the week once, the results are saved and I only subsequently re-run the past couple of weeks. That gets messed up whenever I find an older poll to include or change the current poll window size.

Each of these election analyses posts requires about an hour of my own time. A lot of that is writing about the polls and generating and uploading the extra state poll graphs.

If I skipped the “new polls” table and discussion, a post would only take about 10 minutes to tweak, once the analysis is done. Of course, hunting down and entering polls takes some time on top of the analyses.

16. Darryl spews:

greg,

Thanks! I’ve stuffed it into the database…and not under ND.