Sunday, November 4, 2012

Final NBC/WSJ Poll - November 4, 2012

Likely Voter, 1475 sample size, Obama leads 47.5025-47.4975, 3% undecided.

If you haven't noticed my irritation with RCP and poll reporting, the lead numbers above should give you a clue.  The top line numbers are reported as "Obama +1" then you read into the article and find out that
Mr. Obama led his rival by a whisker, 48% to 47%—a difference of seven voters among a pool of 1,475 surveyed.
1% out of a pool of 1475 is 147 voters.  7 out of a pool of 1475 is 0.005%.  Honest reporting of this poll would declare it tied.

As I did with the Battleground poll, I am changing their method of sample determination.  They use a metric of "leaning" Independents, which obviates the concept of partisan turnout.  The last time I looked at this poll the D/R/I was 44/38/18 or D+6.  The following is their sample data:

The proper identification of the partisan ID for this poll is 31/26/41 or D+5.  Additionally they report that Independents favor Romney by 7, however the "leaning" independents favor Romney by 3.  This leads to an overall Independent support of slightly over 2 points (remember that was 7% of a 14% subsample).

When we adjust this result to the different models, we get the following results:

O+0.005 - Current result
O+1.5 - 2008 turnout
R+1.9 - D+3 turnout
R+4.5 - 2010 turnout
R+4.6 - 2004 turnout
R+6.6 - Rasmussen Party ID

This represents about a 1 point shift toward Obama since the last time the poll was run, but Romney retains a comfortable lead in all possible turnout scenarios.

Going through the crosstabs, one omission stands out when looking at specific issues of importance to the electorate:

The voters are not asked who would be better dealing with the economy or jobs.  These two issues are 3 times more important to the voters than all other issues, when asked in other polls.  The fact that the pollster doesn't even ask is telling.

In summary, this poll does not attempt to predict who will win the race.  Leaving the result at 47.5-47.5.  However, using the models, it is predicting the following results:

If turnout is D+3 Romney wins 50.5-48.5
If turnout is Even Romney wins 52.5-48
If turnout is R+2.6 Romney wins 54-47.5


  1. Agree with your analysis - and the omission of the economy in an economic year election is baffling. I'm looking forward to your analysis of CNN and Gallup/USA Today BG polls.

    Looking at the internals of all the polls the race is tighter this week than last - but I think that Tuesday is looking like 50 to 48 in favor of Gov. Romney. If that 50 to 48 runs true in the BG states Mr. Barone and Will are spot on with a 300 EV for Gov. Romney. Hope you're okay with my chiming in!

    1. Happy for everyone to provide an opinion :)

    2. Thanks Dave. It's been awhile since I've done this - but I do a lot of regression analysis and other statistical tests with Doc Candidates and Grad Level students.

      I really think this is going to be a turn-out election. If the Dems match 2008 - and to do so there will lines miles long due to lower early vote (other than Nevada) numbers - it will be a long night - and is a jump ball as GOP base is probably as strong as 2004. I don't "think" they will match it.

  2. The exclusion of the economy in that poll, to me, is beyond baffling and nobody in the media will ask why.

    Once again, great analysis.

  3. Dave-
    Love the site, just a quick nitpick:
    1% of 1475 is 14.75, 7 out of 1475 is ~.5%, not .005%,
    staring at the numbers too long?

  4. Thanks, Dave and everyone.

    (Now, I'm worried about turnout in VA).

  5. Just went to Fox and watched a Chris Wallace 7 minute interview with Rich Beeson, Romney Political Director. He's strikes a confident pose, but I realize both sides are posturing right now, as Axlerod did before him.

    I watched Rove last night--he was pretty confident about Oh and Fla and NC. He did say that he believed they'd take VA but they had to get the small town turn out and was hopeful there'd be no snow to stop those rural voters from turning out. I know they want to get a lot of the evangelicals to turn out--wonder if they're somewhat worried about that happening to the extent they need it to happen.

    Anyway, in this interview Beeson mentions VA and says it's tight--that scared me as for weeks Romney has been up by about 2 pts there. He told Wallace, upon being asked how long a night it would be, that RR would win big and while he wouldn't commit to stating what time of night, he repeated "big." He said they'd know when certain returns from NH, named a few Midwest counties, and voting totals from Northern VA. Northern VA is blue, fed workers, so I'm wondering if they're anxious to see if Pentagon workers, military from nothern Va give them a boost. Anyone know anything about VA polls?

  6. Here's the link to the interview.

    I got off track here with my post. I meant to point out that Wallace, like all anchors, it seems, was only interested in the polling that shows Obama up. Beeson never responded by explaining those polls assumptions. Instead, he just kept saying turn out, spurred by enthusiam, would win the day.

  7. Anon...
    Early voting in Northern VA is not going well for Democrats. They are lagging in their 08 numbers - and the model that Democrats use for early voting is their "most reliable" voters do so early. The GOP most reliable voters are Election Day voters - and in most BG states they are outperforming 08.

    I have admitted to being a yo yo the past week - mostly because I didn't have any power from Tuesday to Saturday and only could look at top lines from print media - which was unavailable due to the roads/snow. However, the internals are favorable for GOP in the "national polls". Most likely in order for President Obama to win on Tuesday there has to be much heavier on the ground turnout than 08 for the Democrats in order to make up for 1) lower earlier voting raw #'s and spreads in "most" BG states than 08, 2) stronger GOP earlier voting (the margins are tighter and more raw #'s for GOP) 3) GOP intensity which is much higher than 08 and matches that of 04.

    1. Agreed. The uncertainty isn't in Obama underperforming, but the intrinsic uncertainty of the future -- Obama could turn-out 2008+ numbers on election day...

      Given the emphasis the Obama campaign has put on voter ID and early voting and the across-the-board underperformance of this effort, this just seems an ever diminishing possibility.

      Naively, if Obama's Early Voting (EV) is this weak, I'd anticipate a pair-wise loss in his Election Day voting. In fact, a little greater loss as early voting is more a function of organization and the party hardcore. People can be hounded to vote over weeks. Election Day voters are more soft voters.

    2. Good news, thanks.

      I also just saw the full page ad taken out in the WA Times by scores and scores of generals, led by Tommy Franks, and other military leaders, for Mitt for Commander-in-Chief.
      I wondered at first why they had waited so late as it seems that could have helped earlier in CO, and OH, but it's obvious they must have planned it that way to get VA votes, don't you think?

      Perhaps had they done it earlier the Dems would have screamed, "Yeah, look, Romney's a war-monger."

      It's pretty damned embarrassing when all those guys essentially say they wouldn't have wanted you as their Commander-in-Chief. Maybe this is a reaction to Benghazi. Would have been nice to see it in the WAPost or NYTimes, but again, I think it was targeted to VA.

  8. We don't have early voting in CA, just absentee voting and anyone can, if they apply, get an absentee ballot.

    When I saw the voting lines in FLA the other day, Friday, I believe, I wondered why should people have to wait that long to vote. I live in a populous county in the Bay Area of CA, and even when I didn't vote by absentee ballot, I rarely had to wait in line at my neighborhood polling place more than 15 minutes and that was only if I waited until a couple of hours before the polls closed. There are usually three or four draped cubicles in someone's garage and people vote throughout the day. Sometimes I went in the morning before work; most often I went after work, although it's true that I got off work earlier than most people. I think the turnout in my middle class neighborhood was probably as good as turnout elsewhere. Also, we still use paper ballots in my precinct. Anyway, those lines just astound me.