News

Loading...

Monday, October 29, 2012

Dylan Byers: Confused About "Chance of Winning"

Here:

"So should Mitt Romney win on Nov. 6, it's difficult to see how people can continue to put faith in the predictions of someone who has never given that candidate anything higher than a 41 percent chance of winning."

What kind of clown is this guy? With the prediction quoted Silver is claiming, in essence, that if we held this election 100 times, Romney would win 41 of them. So if Romney wins this election, that's that? Silver is done for as a prognosticator?

Then Byers doubles down: "For all the confidence Silver puts in his predictions, he often gives the impression of hedging."

Uh, duh. That's what it means when he doesn't announce that Obama has a 100% chance of winning.

10 comments:

  1. I thought, "Surely this guy can't be as dumb as Gene is making him." So I clicked on the article, and I was right: He is even dumber. The quotes he included from Silver are crystal clear, and this guy is actually breaking a sweat to invent ways to make Silver look bad. It's almost impressive.

    ReplyDelete
  2. Is this an example of what Mises called 'case probability'?

    If so, is that what Silver is actually criticizing him for? (without knowing the terms Mises used, but rather just on a gut feeling)

    ReplyDelete
    Replies
    1. It sure is "case probability." I think that really the best meaning we can give it is that these are what the prognosticator would take as odds: Silver should be willing to accept any bets for Obama at less than 7-3 and for Romney at greater.

      "If so, is that what Silver is actually criticizing him for?"

      Not sure what you mean here.

      Delete
    2. "If you tell me you think you can quantify an event that is about to happen that you don`t expect, like the 47 percent comment or a debate performance, I think you think you are a wizard. That`s not possible," Times columnist David Brooks, a moderate conservative, said on PBS earlier this month. "The pollsters tell us what`s happening now. When they start projecting, they`re getting into silly land."

      Brooks doubled down on this charge in a column last week: "I should treat polls as a fuzzy snapshot of a moment in time. I should not read them, and think I understand the future," he wrote. "If there’s one thing we know, it’s that even experts with fancy computer models are terrible at predicting human behavior."

      I'm wondering if [part of] his critique is basically that case probability is subjective and that trying to quantify it is silly.

      Since you and Dr. Murphy are calling this guy 'dumb' and a 'clown', I'm also wondering if you two believe this specific criticism is valid (or even if you disagree with it, reasonable) or not.

      Delete
  3. Paradox, I think you are ina muddle as to who is critizing whom. Brooks is critizing Silver; Murphy and I are critizing Byers. Read through this again, and if you are still puzzled I'd be happy to answer questions.

    ReplyDelete
    Replies
    1. Oh no, I gotcha, I was saying Byers was using Smith's quote as an argument.

      Delete
    2. Smith?! Who the heck is Smith?

      Delete
    3. Brooks. Geez. I have no idea why I said that.

      Delete
    4. I am saying Byers is using Brook's quote as an argument and I'm wondering what you guys think of that argument. Although you call Byers out for specific arguments, I'm wondering if you would classify Brook's argument along with the quotes you have in the original post.

      Haha, I hope this is clear now.

      Delete
    5. OK, Paradox: I don't think it is silly to put a number on something like Silver's prediction, so long as one does not take it as more than it is. As I said, if read as Silver making book on the election and offering the odds he publishes, it is perfectly sensible. As far as "knowing the future," well, that is precisely why Silver does not give a 100% chance!

      Delete