Most Read
Image 01 Image 02 Image 03

Our numbers guys can beat up your numbers guys

Our numbers guys can beat up your numbers guys

I have received a good reaction to my post, If Nate Silver cannot be wrong, how can he be right?, in which I call non-statistical BS to Nate Silvermania.

Dan McLaughlin, On Polling Models, Skewed & Unskewed examines Nate Silvermania, and links to me for a non-numbers reason, which is good because I’m not a numbers guy:

Poll analysis by campaign professionals often involves a large dollop of conscious partisan hackery: spinning the polls to suggest a result the campaigns know is not realistic, in the hopes of avoiding the bottom-drops-out loss of voter confidence that sets in when a campaign is visibly doomed.

For the record, unlike some of my conservative colleagues, I don’t think Nate is a conscious partisan hack. I have a lot of respect for his intelligence and his thoroughness as a baseball analyst and we have mutual friends in the world of baseball analysis, and I think he undoubtedly recognizes that it will not be good for his credibility to be committed to the last ditch to defending Obama as a prohibitive favorite in an election he ends up losing.

(It’s true that the 538 model is just probabilities, but as Prof. Jacobson notes, Nate won his reputation as an electoral forecaster with similar probabilistic projections in 2008; if you project a guy to have a 77% chance to win an election he loses, that will inevitably cause people to put less faith in your odds-laying later on).

Here’s Dan’s conclusion:

We can’t know until Election Day who is right. I stand by my view that Obama is losing independent voters decisively, because the national and state polls both support that thesis.

I stand by my view that Republican turnout will be up significantly from recent-historic lows in 2008 in the key swing states (Ohio, Wisconsin, Colorado) and nationally, because the post-2008 elections, the party registration data, the early-voting and absentee-ballot numbers, and the Rasmussen and Gallup national party-ID surveys (both of which have solid track records) all point to this conclusion.

I stand by my view that no countervailing evidence outside of poll samples shows a similar surge above 2008 levels in Democratic voter turnout, as would be needed to offset Romney’s advantage with independents and increased GOP voter turnout.

And I stand by the view that a mechanical reading of polling averages is an inadequate basis to project an event unprecedented in American history: the re-election of a sitting president without a clear-cut victory in the national popular vote.

Perhaps, despite the paucity of evidence to the contrary, these assumptions are wrong. But if they are correct, no mathematical model can provide a convincing explanation of how Obama is going to win re-election. He remains toast.

DONATE

Donations tax deductible
to the full extent allowed by law.

Tags:

Comments

Nate Silver is about all that is keeping a lot of Collectivist heads from exploding, so perhaps that is a net good.

It seems an odd thing to have to face, though; spin an improbable win, or tell people the truth and protect your credibility.

I guess if Silver projected a Romney win, he’d be accused of making it happen. Such is the understanding of cause >>> effect in the Collective.

My favorite pollster said, “It ain’t over till its over.”

I notice most of the pollsters are avoiding like the plague 2010 election results as a staring point. Maybe still in denial of its significance.

Of course, the following is purely anecdotal. I live in a blue area (about 25 miles from San Francisco) in a blue state (CA) and walking the dog this morning here is what I see: no Obama lawn placards and no (not one) Obama bumper sticker. In 2008, I was absolutely inundated with Obama/Biden Hope and Change signs. At a minimum, I hope this means that the Obama turn out will be miserable. I’ve already voted for Romney via absentee ballot. Of course, my vote will be drowned out by all the “geniuses” from Stanford (Palo Alto) which is less than 10 miles away. Oh well, I tried.

    This is my experience too. I live on the border of Oakland and see very few O signs and stickers. In 08 I didn’t see a lot of that either, but there was plenty of t-shirts, etc. No merchandize now. 95% of yard signs are for the local elections. It’s like a national election sign would be gosh.

I would suggest that “a mechanical reading of polling averages is an inadequate basis to project” ANY semi-close election. Silver’s model may (or may not) represent a better approach to synthesizing polling data, but it’s still “garbage in, garbage out.” Polls don’t necessarily capture ALL of the information that’s relevant to deciding races, especially close ones. Silver’s slavish adherence to top-line poll numbers, to the exclusion of any other factors or analysis, seems ridiculously narrow-minded.

Even in baseball, an endeavor in which success or failure does not depend on the vagaries of public opinion, statistical analyses still cannot predict precise outcomes. Systems like PECOTA may represent a BETTER way to analyze raw data, but no sensible GM or manager would operate exclusively on the basis of a player’s prior-year stats in making decisions. There’s still a role to be played by subjective, experienced judgment.

I must say that I followed Silver’s baseball work fairly closely and it was excellent.

There was a time in my life when I would have read the conclusion that the Democratic candidate “is toast” and felt despair. Now I feel elation.

Check out this study by lefty Third Way on party registration since 2008. Ugly for Dems:

http://content.thirdway.org/publications/605/Third_Way_Memo_-_Rage_Against_the_Machine-Voter_Registration_Update.pdf

Upshot: Dem registration not up, GOP registration up, Indy reg waaay up – and Romney is up among Indies, so….

Mmm, mmm, mmm, Willard Mitt Romney.

Remember, it’s not who votes, its who counts the votes.

A number of confident people on the Right are confidently predicting a Romney victory.

You know what would make me more confident about a Romney victory? Seeing those confident conservatives take confident advantage of the 2:1 Intrade odds against Romney.

(I don’t see leftist partisans rushing to Intrade either, despite the chance to make 50% on their money in a week.)

    gs in reply to gs. | November 2, 2012 at 1:25 pm

    (I don’t see leftist partisans rushing to Intrade either, despite the chance to make 50% on their money in a week.)

    Actually, Nate Silver is putting his money where his mouth is.

      gs in reply to gs. | November 2, 2012 at 5:06 pm

      Thumbs downs. Gee, some Confident Conservatives sure are sensitive, aren’t they?

      But that’s not what I logged in to say—

      Robert Verbruggen at the Corner notes that Silver’s offer of a bet is disingenuous: if Silver is 80% confident of an Obama victory, he should have offered odds. Too bad Scarborough didn’t call him out on that.

SHOCKER. Rasmussen now has it tied, 48-48. A few days ago, Romney was up, 50-47.

I hate to say it, but…I’m tired of polls. My gut feeling is that between Romney’s incompetent summer-month campaigning and Democrat vote-stealing, we’re going to get 4 more years of Obama.

    SHOCKER. Rasmussen now has it tied, 48-48. A few days ago, Romney was up, 50-47.

    Reaction to the hurricane?

      CalMark in reply to gs. | November 2, 2012 at 12:32 pm

      Probably.

      But the result is the same. Apparently, the disaster (and Christie’s love-notes) couldn’t have happened at a better time for the Phony-in-Chief.

      “People eventually get the government they deserve.”
      — George Bernard Shaw.

      “Eventually” is HERE. If people vote Obama in again, Americans deserve everything they get. (I, for one, will have to move back in with my parents for the foreseeable future. I’ve been unemployed for the vast majority — since August 2010 — of Obama’s first term.)

      It’s probably going to change over the weekend as people will see problems with how the relief is handled. Granted, some problems are inevitable when we have a disaster of this proportion. But there are clearly bone-headed decisions being made and POTUS is nowhere to be found, at least for now.

Probably what’s stopping conservatives from wagering real money on Romney is that, if Obama wins, we’re really going to NEED the money we bet on Mitt in order to pay for higher taxes, higher gas prices, higher health insurance premiums, etc. The conservatives are probably mostly placing their wagers on Obama as a hedge against the financial havoc he is going to wreak on us if he wins four more years.

I’m going with that think tank gang from the University of Colorado that is forecasting a Romney landslide.

• Unemployment over the magic number
• Record low employment levels
• BenghaziGate
• Fast and Furious
• Gitmo still open

Feel free to add your own…

This may be more material than prediction markets and inconsistent polls:

WASHINGTON (AP) — Americans’ confidence in the economy surged last month to the highest level in nearly five years, as many were encouraged by an improving job market.

The Conference Board said Thursday that its consumer confidence index increased in October to 72.2. That’s up from 70.3 in September and the highest reading since February 2008, two months into the Great Recession. Investors cheered the news.

The survey is watched closely because consumer spending drives nearly 70% of economic activity. The reading is still below 90, a level that indicates a healthy economy. It last reached that level in December 2007. But the index is far above the all-time low of 25.3 touched in February 2009.

The gain in consumer confidence could be an encouraging sign for President Barack Obama, who faces re-election Tuesday at a time when the economy is the top issue for most voters.

Afaic the increase does not qualify as a “surge”, but the point in the final quoted paragraph remains.

    Henry Hawkins in reply to gs. | November 2, 2012 at 1:32 pm

    I’m not sure the voting public will see a one point uptick from Horrible Economy to Economy Sucks Big Time as encouraging at all.

    Look Dad! I improved my math grade! From F+ to a D-!

Henry Hawkins | November 2, 2012 at 1:29 pm

Geez, the Eeyore Brigade is out early today.

Assuming any poll is accurate… one consistent detail of all polling to date has been Obama’s inability to rise above 48%, with 46 and 47% in most polls. Romney has crested 50% in only a few polls and lkikewise hangs around 46-48%. So, there remains a decisive number of undecideds at 4-8%. Which way will they break? Historically, they break about 70% for the challenger, which means a Romney victory. What would make current undecideds break for Obama instead? I don’t think Hurricane Sandy will cause that, especially as things are getting a little uglier every day in NY/NJ’s recovery. Even if it did, is it offset or bested by negative reaction to the burgeoning Benghazi cover up?

I see Romney’s approval numbers on jobs & economy, his double-digit lead among independents, plus I factor in that the 2010 midterm landslide meant something and this time Obama himself is on the ticket for voter retribution and I believe we are looking at a decisive Romney victory.

One thing is certain: Rasmussen’s credibility will be shot with conservatives, the only people who take him seriously.

A week before the election, Rasmussen has Romney repeatedly at the magical 50% when Romney (anecdotally) has momentum, but as momentum should be building, slides Romney back down to 48%.

Regardless who wins, Rasmussen is inconsistent. It’s not so much the percentage swings, but because the significant apparent “momentum shifts.”

    CalMark in reply to CalMark. | November 2, 2012 at 1:58 pm

    Just to add: Ohio polls show independents all over the place. Most of them show Independents for Romney between 7 and 20+ percent. Rasmussen has one of the worst independent counts for Romney, OBAMA+3; overall, Obama 49-46.

    I want to vote and for this to be over.

    P.S. Rush Limbaugh sounds scared and defensive today. Going on and on about “meaningless” anecdotal and external things, playing a Romney sound clip whose cheers/applause frankly (and it hurts me to say this, because I was inclined to hear something different) sound a lot smaller than Clinton’s for Obama.

      creeper in reply to CalMark. | November 2, 2012 at 2:45 pm

      I suspect Rush is demoralized for the same reason I am–the unrelenting cover-up by the media of the Libyan debacle. Like me, he probably held out hope that today would bring a firm denial from someone…anyone…at State, the CIA or our military, that Obama ever ordered anyone to go to the assistance of those brave men. Instead…crickets.

      This story should have Americans marching on Washington with torches and pitchforks. Instead, it’s being buried by the most corrupt media in our history.

      No wonder Rush is down. It’s hard to remain positive when you see the media stealing yet another election for Barry.

All one needs to know about Nate (the snake) Sliver – he use to be prominently displayed on the Daily Kos. He’d already started down the road to perdition 5 yrs ago. Along with selling his soul to get his NYT gig, like others there, he had to put his objectivity into their lockbox, and sign a prog loyalty oath. Once he’d met these requirements he transformed from “the snake” to the “shill”.

Easy test. Nate predicts Obama re-election at 76%. Isn’t that 3:1 odds. Ask him to bet on it. Ok, be sporting and offer him 2:1 odds. As shills and snakes are wont to do, he’ll beg off at any odds. Make the bet to his favorite charity. What passionate, caring prog could resist?

rightatthebeach | November 2, 2012 at 3:35 pm

CalMark is a moby, not an Eeyore. I have been watching his comments for a while now and his only purpose is to try and depress Republican turnout. Busted, Cal Mark.

Rush was fine today, he ripped NBC a new one, that is for sure. Rasmussen is taken seriously by everyone, not just conservatives. Cal Mark lives for polls and delights in pointing out any where Obama is up even a tick but ignores the internals.

I suspect Creeper is a moby, too. Time will tell.

    “Busted.” ‘Cause you said so?

    This is beginning to feel a whole lot like ’92, when Clinton came roaring back from a tie. It also feels a whole lot like ’08: we’re all parsing polls, trying to find subjective things (rallies, “energy,” “momentum”) to be positive about.

    I hope Romney wins. I really do.

    However I’m seeing a shift to Obama, who’s suddenly doing a whole lot better. Also, I’m trying to be honest with myself: I was happy when Rasmussen had Romney up at 50 for quite a few days, but now he’s back to 48 — very bad, this late in a campaign, especially for a challenger. Remember: that’s a daily tracking poll, meaning it incorporates a polls from several days.

    So, call me whatever names you like. I hope everyone gets out and votes for Romney. I was feeling better, when Gallup and Rasmussen had Romney surging; now he’s moving backward. I’m also tired of all the “Obama is gone!” triumphalism on the conservative web.

    We shall see.

      annoyedbeyond in reply to CalMark. | November 2, 2012 at 8:49 pm

      Funny, Rush sounded fired up to me. And he was playing sound from a Romney event with a huge crowd–many many times the size of the Clinton crowd you’re babbling about. You may not be a moby (I think you are) but you’re definitely a purveyor of ‘fear porn lite’.

        Henry Hawkins in reply to annoyedbeyond. | November 2, 2012 at 11:32 pm

        We recently conducted a psychic exploratory on CalMark and determined that as a conservative living in California, what appears to be mobyism or eeyorism is an understandable reaction to his situation and environment. An extraction team is being formed.

I choose to be positive at this point. I have thought, since the first debate, that it will either be a Romney landslide or an obama squeaker. We will not know until Tuesday evening, but I think America is ready to throw this clown out. My wife chose to vote early today at the courthouse in Rapid City, SD. (I’m going to vote on Tuesday at our normal polling place.) She said there were lines to vote at the courthouse, and this is is deep red “West River” territory of South Dakota. I think this is a small (albeit anecdotal) clue that people are inspired to vote and get this incompetent SOB the hell out of the White House. Bill Jacobson is, and continues to be, a candle in the darkness whose encouragement has helped keep me out of despair these past several months. Be positive. Vote!

Font Resize
Contrast Mode
Send this to a friend