• AmbiguousProps
    link
    fedilink
    English
    arrow-up
    6
    arrow-down
    8
    ·
    3 months ago

    Nate Silver’s polling has been wrong before and it will be wrong again.

    • triptrapper@lemmy.world
      link
      fedilink
      arrow-up
      3
      arrow-down
      8
      ·
      3 months ago

      He’s wrong very frequently. He had a couple amazing parlays and people think he has some special sauce.

      • lennybird@lemmy.world
        link
        fedilink
        English
        arrow-up
        24
        arrow-down
        1
        ·
        edit-2
        3 months ago

        People who say this don’t ever really back this up. Nate Silver has pretty consistently maintained >90% accuracy across not just presidential races but primaries, gubernatorial, and congressional races. Ultimately thousands of races. Remember, he his probability != a prediction. Just because someone has 70-30 odds doesn’t mean they win 100% of the time. It means if that race was run 100,000 times, 30,000 times would be a loss. Accuracy can be determined by grouping a sample of such 70-30 races to see if they follow that trend. Lo and behold, Nate’s algorithm generally does.

        Obviously events change and predictions cannot rapidly factor in, say, Comey’s October Surprise…but in this era of absurdity, I’m not sure we really have any more shocking surprises that can top what we’ve already seen and know.

        These are good markers to see how messaging and strategy for each side is working and whether a change needs to happen. It should have zero bearing on voting which everyone should do whether you’re winning in a landslide or not.