Skip to comments.My apologies to Nate Silver
Posted on 11/07/2012 9:08:42 AM PST by Raycpa
My apology to Nate Silver. I doubted your statistics. I assumed you were a smug know-it-all type numbers guy. You were right and you had a right to be smug.
I hear ya. ; )
I said all along that Nate Silver is the ONLY poll analyst worth listening to. Ignore EVERYONE else.
Ditto. I thought he had to be full of sh*t, but damn, his accuracy was uncanny. He was dead-on.
Instead, curse Barone.......
agreed.. he nailed it..
I am so surprised he was right. I expected more of our citizens.
If he knew obama was losing 10 million votes from what he had in 2008 why didn't he speak up?
RCP final poll average of each & every state also predicted each and every state correctly including Florida.
RCP ran a very simple algorithm - called average.
Nate Silver added a lot of weightings and secret sauce and what not.
Both of them ended up with the same result.
Wow, I’m surprised to see so many naive people on Free republic of all places. Nate Silver did not predict the outcome, he used his position to influence it. It came out to be about the same, because that’s what they’ve been working towards this whole time, by discouraging Republicans, harassing them at the polls and rigging voting machines.
In 2008...optimism among many (not me) reigned supreme. All we heard about was oversampling of dems...and anecdotal evidence about record turnout at their individual polling places. Republican turnout as described as mammoth.
Forward to 2012. SAME story...except this time I expected a landslide. All we heard about was "That poll is crap. D+8? YEAH RIGHT!!!" All we heard yesterday was story after story of record turnouts.
It all turned out to be crap. Any FReeper in ANY future elections who talks about a poll being garbage because of their D sample...I will simply remind them of yesterday.
RCP's average in Florida was Romney +1.5, two percentage points away from the final result.
Two surprises for me that threw my analysis off.
1. I never guess D turnout would be almost as high this time as last time. WRONG.
2. I assumed there would be movement towards the challenger as the race ended. WRONG.
I’m still not exactly sure how Silver knew both of those things, especially the second one, or how Axelrod and Plouffe were so confident the election was totally in the bag.
I give them my grudging respect though. Those guys nailed it. I hate them all, but they nailed it.
Shows that, if anything, polls are biased towards republicans. A GOP candidate needs to be up 2-3 points in order cover union and democarat turnout machine.
Let’s not go overboard. Likely he just gets Obama’s internal numbers handed to him.
You are right. But it’s still great. No fancy algorithm, no secret sauce (whatever that means). Nate got 1 state better than them. And even Nate gave Obama just 50.3% chance of winning Florida.
I actually doubt all the polls because I understand a little bit about sampling because I use it for auditing. I’m trained to be skeptical of my own results. I also have a great deal of respect for the polls done and am very hesitant to challenge a poll because the internals seem wrong.
My issues with Nate’s analysis was twofold. I thought he was cherry picking which polls to use and was adding bias instead of decreasing it. Second, his translation of his analysis into a certainty factor to the nearest 10th decimal inferred an accuracy level that is not sustainable from the data.
But he was right.
Let’s not go too far here. Silver may have his own model, own way of doing things, but when it comes down to it, all Silver did was create a weighted average of poll results. Silver was right, not because he’s a genius, but because the polls were right.
Exactly. Nate Silver (and even more, Sam Wong) are just the messengers, the polls they were aggregating wrote the message.
My big take away from the Silver/Wong results over time: the race remained pretty much in the same please since last summer, with most actual eventual voters having made up their minds well in advance of Nov. 6th. and most of the dips and rises for either candidate reflected differences in survey response rates due to partisan enthusiasm.
The outcome, in light of the polling, makes a *lot* more sense if that was the case.
I too said to listen to Silver and was attacked for it. Do NOT question big data and predictive analytics. It is very powerful.
“My big take away from the Silver/Wong results over time: the race remained pretty much in the same please since last summer, with most actual eventual voters having made up their minds well in advance of Nov. 6th. and most of the dips and rises for either candidate reflected differences in survey response rates due to partisan enthusiasm.”
That does make sense. To his credit, actually, I believe Silver made the same point a while ago. He commented that some of the rise in Romney’s polls after the first debate could have come from Romney voters who, because of Romney’s strong performance, were more willing to talk to pollsters.
I’m not sure that all of the poll fluctuations are attributable to differing response rates, but it is a plausible hypothesis, especially given our “endless campaign” political culture. After 2 years of nonstop campaigning, and 24-hour cable coverage of that campaigning, it’s certainly plausible that most people made up their minds months ago.