Thursday, October 25, 2012

October 25, 2012 Ohio Update

Rasmussen updated his Ohio poll to reflect movement toward Romney, and a tie.  Also, Survey USA released a new poll which did not change from their last Ohio poll.

The big news last night was the Time Obama +5 poll, that everyone was concerned about.  Don't be.  It is a D+10 poll where Independents favor Romney by 14 points.  Also, someone made a math error in the poll, because when I add up the respondents, I get 694 likely voters/already voted.  Not the 742 that they are touting.  In any case, putting their numbers through my Ohio model, we get:

R+8.64% - Using the 2004 turnout model
O+1.28% - Using the 2008 turnout model
R+5.27% - Using the 2010 turnout model
R+4.54% - Using the 2012 registration model
R+2.24% - Using a D+3 turnout model

In other words, it is exactly in line with the other Ohio polls, off by a few tenths of a percent in all turnout models.  The Ohio averages now include 8 polls, so the fidelity is getting to be pretty good.

Polls included:
O+3 - Survey USA
Even - Rasmussen
Even - Gravis
O+5 -Quinnipiac
O+1 - PPP
O+3 - Fox
Even - Suffolk
O+5 - Time

O+2.13% - Current RCP Average
R+8.83% - Average using the 2004 turnout model
O+0.64% - Average using the 2008 turnout model
R+5.61% - Average using the 2010 turnout model
R+4.89% - Average using the 2012 registration model
R+2.72% - Average using the D+3 turnout model

The results shifted less than 0.05% in all of the reweighted models.  Romney continues to lead Obama by a comfortable margin.

12 comments:

  1. No wonder President Petulant is reduced to flinging curse words. :-) Good news and thanks for the update - and all the work you do here.

    ReplyDelete
  2. Hey Dave, thanks as usual.

    I don't seem to remember where the 2012 registration model is from, could you point me in the direction?

    ReplyDelete
    Replies
    1. Yeah, it is from an analysis a couple Ohio State professors did trying to figure out what the Ohio registration numbers are right now. Since Ohio doesn't have party registration, you can't get it from the Secretary of State's web site.

      Now, of course, I can't find the link. I thought it would be important when I started doing this, but now I kind of ignore it. The two numbers I watch are the D+3 and the 2010.

      D/R/I from that one is 37/37/26.

      Delete
    2. Thanks, I'll take a look around for the dataset later tonight.

      One more question and I don't mean to be an asshole. I'm totally behind you nationally, just trying to get a feel for the state numbers now.

      So, assuming that split you wrote was for the OSU model, 37/37/26 was also 2004's split according to CNN's exits -- shouldn't they both output the same value?

      Also, your partisan-split variables for each timeslice are for OH or national?

      Delete
    3. No, I use the Ohio partisan splits for Ohio in the Ohio rebalance. National exits for the national numbers. In 2004 Ohio was R+5, but nationally dead even. So the Ohio 2004 number is a really really good GOTV. In 2004, Ind split toward Kerry pretty well, but Bush still won Ohio handily by getting people to the polls. Rove was a turnout genius that year.

      This is why I don't buy these Ohio polls. We have proof that the GOP can get their people to the polls at a very high rate in Ohio, if they put their best effort into it.

      Delete
  3. Yep and I suspect the Romney campaign has been all over GOTV in Ohio.

    http://www.powerlineblog.com/archives/2012/10/whats-happening-in-ohio.php

    ReplyDelete
  4. hey Dave...do you have any similarly soothing data on Florida. I've seen a couple of news items that make it look like the Dems haven't quite conceded the state yet after all, despite reports to the contrary.

    ReplyDelete
    Replies
    1. No, and not going to bother. Romney is winning the I-4 corridor, and that means he will win Florida. There is a lot of Dem activity here, but the Obama ads have tapered off. Nelson looks like their best chance to hold a vulnerable seat, so they aren't going to walk away.

      But Romney will win Florida.

      Delete
    2. Thanks Dave. Sure would be nice to be rid of Nelson, too.

      Delete
  5. Dave, here is what has been bothering me about the media reporting in OH, and you could confirm for me that it is screwy. Almost invariably when OH polls are discussed on TV, they say that 0bama is holding on to his advantage because of the popularity of the auto industry bailout. Nobody ever says how they know this, it is just The Truth. But this is a testable hypothesis. And not just by asking the question in a poll. If the popularity of the bailouts were driving 0bama's poll lead in OH, then you would expect to see his numbers to be better in OH than nationally AMONG ALL partisan demograhpics, because the explanation is not partisan, it is geographic. But I don't think that is what the polls show, is it? Instead, his advantage is due to an outsized Democrat turnout. Whether that happens or not, that is NOT something that one would expect due to popularity of auto bailouts. The whole country knows about those, so if they were so popular on a partisan basis, that would be reflected everywhere. But if the notion is that people are voting because 0bama saved their own job in OH, then you would expect to see that among Repubs and Indys. Is that the case?

    ReplyDelete
    Replies
    1. I have no real data to confirm your idea, but it makes sense. One of the things I've noticed, and even Rasmussen does this, is when they are trying to explain a poll, they just make up a reason.

      They don't have any real explanation on why "Obama is holding his lead", so they say something plausible. The possibility that he isn't really leading never occurs to them. I had a long twitter argument with Bret Baier on this, and they just don't get it. "But the poll says!!" Is their default answer. The math behind it seems to be too hard for them to grasp.

      Delete
  6. Is 0bama doing better among Independents and Republicans in Ohio than in the national polls or other swing state polls? If so, then the hypothesis might have merit. If not, and it is all due to the difference in partisan turnout, then it doesn't.

    ReplyDelete