Wednesday, October 24, 2012

A Small, Yet Important Point

A lot of people have noticed that historically, Ohio tends to vote slightly more Republican than the national results.  Going back a number of years, Ohio votes consistently about .5% more toward the GOP than the national share the GOP gets.

I'm also seeing a lot of angst about the Ohio RCP.  "I'd be more comfortable if that would stop showing Romney tied!".

This is where the reweighting I am doing shows the truth of the matter.  Look at the D+3 turnout model.

D+3 national average: Romney +2.17%
D+3 Ohio average: Romney +2.79%

If Ohio has a similar turnout to what is seen nationally, then Ohio will show .62% more support for Romney than his national share.

Quit stressing out about Ohio.

15 comments:

  1. Dave, have you seen anyone from the Romney campaign, or a surrogate, or even a Republican official, claim that they think they are slightly ahead in Ohio? Dick Morris doesn't count... Campaigns are notorious for stating the most optimistic projection of their current standing in a tight race. But I don't see any of them saying they think they are ahead in Ohio, or that Ohio is looking good in their polling right now, or anything. Most seem to confirm that it is a tight race at best, and often the Romney is just very close. Wouldn't you think the Romney campaign pollsters would have some idea about this kind of analysis you are doing? If so, why are they giving no signs of the confidence you have? Or have I missed it?

    ReplyDelete
    Replies
    1. Have you seen any Romney campaign or surrogates claim they are winning North Carolina, Florida, or Virginia? This campaign is very conservative in their statement and their polling assumptions in turnout. Their pollster publicly claims they expect a D+3 turnout, despite Rasmussen and Gallup showing that D+0 is the likely result.

      Besides, the Obama campaign is now talking about how "they can win without Ohio".

      Romney is ahead in Ohio. I have 9 data samples showing that he is.

      Delete
    2. I think I have, actually (the anonymous comment above is from me, BTW). Not bragging or taking anything for granted, but definitely have seen claims that they think they are ahead or feel good about how things are. It seems like the comments I see about Ohio are generally more conservative than even that, indicating a deficit still to be made up. But maybe not. Could just be my own pessimism. Rasmussen showing 48-48 today was a boost. I'd like to see a red number show up though. OH would be the final straw in the preference cascade. 0bama collapses on a national scale if OH no longer seems in the bag in the polling average.

      Delete
    3. It's a double edged sword to brag that you're going to win.

      If either Romney or Obama strutted around and said their internal polls show them easily winning, that kind of cockiness will turn off many late-deciding voters.

      I think Romney will pull it out in Ohio, but I don't think it's in the bag.

      If after 4 years an incumbent President can't get above 47-48% in the Ohio polls (even with optimistic Democrat turnout assumptions) despite throwing EVERYTHING they have at it, that tells me he's probably going to lose.

      My gut feeling as to why Romney has had such a hard time closing the sale in a normally Republican-leaning state is Ohio relies heavily on manufacturing, and the "Bain Outsourcer" ads and Romney's unfairly maligned position on the auto bailouts have probably pulled him down further than a generic Republican candidate with more populist roots.

      Delete
  2. ^^^Getting out vote, keeping the urgency high. Up comfortably projects the wrong message. Also, I think it is a little closer than 2.5, and I think D's will be a little more enthusiastic in OH (I live in Columbus). Still think he's slightly ahead and I would give Romney a better than 50/50 shot.

    ReplyDelete
    Replies
    1. If Dems are "a little more enthusiastic" then Romney leads by 4, not 2.5. Romney leads by 2.79% assuming the Democrats turnout at a rate 3% higher than Republicans. They would have to beat their 2010 numbers by 4 points.

      That isn't going to happen.

      Delete
    2. I appreciate you methods and don't disagree with the premise, other than to say your source data is polls... which are fickle...I am thinking of how hard it was to get Kasich Elected in a R Wave election ok, so he one by 2+ I think, which isn't recount close, but it felt up in the air all the way until 11pm that night... the vibe I get from your page is that Ohio is in really good shape and not to worry...maybe I just need to worry...Anyway thanks again for your work and frequent updates...

      Delete
    3. Kasich may not be a good example from 2010. Note that downticket it was a clean sweep for the GOP, so whatever made him doubtful didn't affect them.

      And there's no reason to think that Kasich's issues in 2010 affect Mitt Romney in 2012.

      Delete
  3. Have you seen the new TIME poll putting Obama up by 5 in OH?

    ReplyDelete
  4. Dave - TIME Ohio poll looks like crazy data. Obama up 5 in OH, but poll appears to be D+10 if I calc'd right. And, Romney leads Independents by 23 points! Can you conduct your magic and make us all relax? Thanks for everything you are doing. It is greatly appreciated.

    ReplyDelete
    Replies
    1. Sure.

      First of all, someone can't add. They say it is 742 sample size, but the sub samples only add up to 694. And 694 is a very small poll, generally you need 800 to have any validity.

      Independents support Romney by 15 points, and the D/R/I is 39.33/29.68/30.97. Close to D+10.

      Reweighted:
      2008 - O+2.3
      D+3 - R+1.2
      2010 - R+4.2
      2004 - R+7.6

      Feel better?

      Delete
    2. Whoa, wait a second.

      The 2008 exits were 39/31/30
      This poll is 39/30/31 and D+5 topline

      A reweighting to 2008 is a 1% shift and it drops by 2.7% to O+2.3? I suppose you're replacing voters who are only +15 Romney with +80 Romney voters, but it made me do a double take off top-of-head...

      Delete
    3. Independents have a different preference in this poll than they did in 2008. Also, I'm assigning undecides to Romney 2:1.

      Delete
  5. W had 2,858,727 votes
    Obama netted 2,940,044 votes

    We can say with certainty Obama will underperform 2008 levels due to registration turn-over and atrophy as well as early voting trends. The question is where will Romney fall...

    It might just be the media, but OH is annoying me.

    ReplyDelete