RE: Why Nate Silver predicts an Obama win.

RE: Why Nate Silver predicts an Obama win. (Full Version)

All Forums >> [Community Discussions] >> Dungeon of Political and Religious Discussion

Message

DarkSteven -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 5:09:14 PM)
quote: ORIGINAL: Yachtie quote: ORIGINAL: focalss So I request help on explaining how if the Ohio polls are at 2.4%+ Obama that translates to an 86% chance of winning which is why I am critical of Silver's saying 86%. Loosely, using the 86% chance, it only means that Obama has an 86% chance of actually hitting that 2.4+% win in Ohio. Statistically, if one utilizes Silver's statistical model, that's not a bet one should go against. But like horse racing, it's been known to happen. Nope. Think of a bell curve. That bell curve has its peak at Obama +2.4%. But the entire area under the curve, from Obama +0% and all the other permutations with him winning, is 86% of the curve. quote: ORIGINAL: focalss If the poll had a 2% margin of error lets say and it came in 50 - 49 Obama - Romney then it cannot predict accurately the result unless I misunderstand. You misunderstand, sorta. If these are polls, you're correct. But Silver aggregates polls, and his results have a smaller margin of error than the individual polls do.

DarkSteven -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 5:13:21 PM)
quote: ORIGINAL: truckinslave If Pa goes Romney, it's over. If Va goes Obamao, it's probably over (unless Romney carries Pa) As Ohio goes, so it goes (unless Romney carries Pa) Those other states are just wasting money opening the polls. I see it breaking down to the following: If Obama takes Florida, Virginia, or Ohio, he wins. If Romney takes PA, he wins. So we just need to watch the East Coast returns.

tweakabelle -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 5:26:04 PM)
quote: If Obama takes Florida, Virginia, or Ohio, he wins. If Romney takes PA, he wins. So we just need to watch the East Coast returns. I don't disagree with your assessment DS, but I do wonder if it is worth the $2.5 billion the candidates spent to end up with that simple equation.

DarkSteven -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 5:28:22 PM)
quote: ORIGINAL: focalss However to DYB, the Nevada situation is the most interesting thing that caught my eye on Silver's site. Why is Romney behind in Nevada when it has a large Mormon population, bad economy and he ran the Olympics there? Not a good sign for him and it plays into DYB comment on the other side. If Obama can get more people out for him where are the Mormons in Nevada for Romney? Likewise in Ohio, the groundgame is all now in Ohio. Rove was able to pull out voters in Red districts to go for Bush in 2004 to avoid the Florida 2000 scenario. Given that big cities trend to the Democrat, I still say nothing changed in the Ohio Red Districts (Red = Republican, Blue = Democratic). Reportedly Obama has more workers there but are they going to be able to produce and swamp the Ohio Reds? Nevada: You're right about the Mormons and the economy. However, there is a large Hispanic population as well, and a lot of hourly casino workers that support Obama. However, Romney ran the Olympics in SLC, Utah.

focalss -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 5:32:55 PM)
Nope. Think of a bell curve. That bell curve has its peak at Obama +2.4%. But the entire area under the curve, from Obama +0% and all the other permutations with him winning, is 86% of the curve. quote: ORIGINAL: focalss If the poll had a 2% margin of error lets say and it came in 50 - 49 Obama - Romney then it cannot predict accurately the result unless I misunderstand. You misunderstand, sorta. If these are polls, you're correct. But Silver aggregates polls, and his results have a smaller margin of error than the individual polls do. Without knowing more about the distribution of the bell curve I can't say. It could be a spiky peak or it could be a baseball mound. I did think Silver was using polls to come to his conclusions. I understand some researchers use meta studies to come to conclusions for medical hypotheses because it is incredibly hard to do long term studies on humans and for some other reasons. So if I understand what is going on, and the polls I looked at tonight at 270 to win, with a 1% margin and over 2% margin of error, is that Silver is taking a lot of polls that have Obama a little ahead and coming to the conclusion that he has a better probability than what those smaller polls were ever designed to report which is why I say that anyone with a 2.4% lead doesn't have an 86% chance of winning and certainly a 1% lead doesn't produce an 86% chance of winning.

TheHeretic -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 7:13:07 PM)
quote: ORIGINAL: cloudboy Rich likes to point out the white elephant in the room Not a white elephant, Clouds, just a regular one. The white elephant refers to something entirely different. I guess you aren't familiar with the metaphor, or it would be clear that it isn't the economy, which people most certainly are talking about. Plain old Wikipedia is more than sufficient on this one.

Lucylastic -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 7:14:47 PM)
I prefer Pink elephants, at least you know what you'er about then!

tazzygirl -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 7:45:28 PM)
quote: If Romney takes PA, he wins. Why would anyone assume Romney will take a state he hasnt even polled in the lead for since Feb?

focalss -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 7:55:42 PM)
"However, Romney ran the Olympics in SLC, Utah." Yeah, I was a little off on my geography on that one and I heard the Harry Reid machine is bringing it in for Obama.

DomYngBlk -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:00:43 PM)
quote: ORIGINAL: tazzygirl quote: If Romney takes PA, he wins. Why would anyone assume Romney will take a state he hasnt even polled in the lead for since Feb? Cause he knows he is gonna lose Ohio.....wanted to try plan b.

DarkSteven -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:06:14 PM)
quote: ORIGINAL: DomYngBlk quote: ORIGINAL: tazzygirl quote: If Romney takes PA, he wins. Why would anyone assume Romney will take a state he hasnt even polled in the lead for since Feb? Cause he knows he is gonna lose Ohio.....wanted to try plan b. That's my take on it, too. A Hail Mary pass.

focalss -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:10:57 PM)
quote: Nope. Think of a bell curve. That bell curve has its peak at Obama +2.4%. But the entire area under the curve, from Obama +0% and all the other permutations with him winning, is 86% of the curve. That's not what I think it is. I think the curve is centered at +2.4 ( Tonight CNN reported+4 and +6 in two other polls where 270 says +1 so who knows). Or alternately there is a gap of undecided left in the middle with a shaded area for that and the margin of error in the center. I definitely cannot picture 86% of the voters for Obama. I also cannot picture statistically anything near 86% of the shaded area for Obama.

DomYngBlk -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:11:27 PM)
Then why the thought that he can win the election if he wins PA, DS?

focalss -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:26:36 PM)
I think DS is saying that if PA goes for Romney there is a chain reaction down the line for Romney. On VA, the opposite, without VA its hard to see how Romney wins unless he then picks up PA and Ohio and everything is in play which is a little unlikely.

tazzygirl -> RE: Why Nate Silver predicts an Obama win. (11/5/2012 8:40:27 PM)
PA is highly unlikely.

Edwynn -> RE: Why Nate Silver predicts an Obama win. (11/6/2012 3:25:38 AM)
quote: ORIGINAL: Moonhead Aren't only 49% of the Moomins in Nevada allowed to vote for anybody? (Or is it one of the other flakey American desert pseudo Christian sects who refuse to let women vote?) I'm not saying that you are, but the 49% item brought to mind that you might perhaps be thinking of the Electoral College system in this country, where, in effect, up to 49% of presidential votes in every state are tossed out. Which is why they hammer so hard with the Get Out The Vote, Your Vote Matters, etc., campaigns, so as to divert attention from the fact that if your vote is in the minority in that state, even if a 49% minority, your vote in fact matters not one whit. But the Get Out The Vote et al. such campaigns are so greatly championed by the same media psychopaths (which is to say, essentially, all media in this country) that came up with a way of further marginalizing any potential political minority, along with encouraging greater divisiveness, by the genius of their "red state"/"blue state" hyper-simplification of the matter. A master stroke of tactical disenfranchisement, that was.

Edwynn -> RE: Why Nate Silver predicts an Obama win. (11/6/2012 3:45:43 AM)
As we can witness here, everybody is concerned with matters of statistical validity, not a single concern about the corporate infiltration of both parties and the thorough infestation of their minions in the administration, the 'regulatory' agencies, and the Congress. Every administration, every Congress, regardless of party or party majority. The only thing holding our interest (for some) anymore is the placing of bets, calling in 'scientific measurement,' etc., in the desperate albeit futile attempt to provide any meaning to a de facto meaningless process.

DarkSteven -> RE: Why Nate Silver predicts an Obama win. (11/6/2012 3:57:28 AM)
quote: ORIGINAL: DomYngBlk Then why the thought that he can win the election if he wins PA, DS? He himself thinks there's a chance. He's making a last ditch effort there. IIRC Silver gives him a 5% shot in PA.

tweakabelle -> RE: Why Nate Silver predicts an Obama win. (11/6/2012 5:05:45 AM)
quote: ORIGINAL: Edwynn As we can witness here, everybody is concerned with matters of statistical validity, not a single concern about the corporate infiltration of both parties and the thorough infestation of their minions in the administration, the 'regulatory' agencies, and the Congress. Every administration, every Congress, regardless of party or party majority. The only thing holding our interest (for some) anymore is the placing of bets, calling in 'scientific measurement,' etc., in the desperate albeit futile attempt to provide any meaning to a de facto meaningless process. Uhmmmm ... not quite everybody Edywnn. I did raise the matter of the c$2.5 billion spent by the candidates and their backers but I'm afraid it didn't elicit any response either. No one bothers to deny the corruption the funding requirements impose on all serious candidates. Even more oddly, no one seems to be talking about changing the situation either. Perhaps it deserves a thread of its own.

Yachtie -> RE: Why Nate Silver predicts an Obama win. (11/6/2012 5:36:18 AM)
quote: ORIGINAL: Edwynn The only thing holding our interest (for some) anymore is the placing of bets, calling in 'scientific measurement,' etc., in the desperate albeit futile attempt to provide any meaning to a de facto meaningless process. Quite so, ultimately. Even bookies are known to sweat bullets at post time[:D]

Page: << < prev 1 2 [3] 4 next > >>

Collarchat.com © 2025

Terms of Service

4.699707E-02