• This is a political forum that is non-biased/non-partisan and treats every person's position on topics equally. This debate forum is not aligned to any political party. In today's politics, many ideas are split between and even within all the political parties. Often we find ourselves agreeing on one platform but some topics break our mold. We are here to discuss them in a civil political debate. If this is your first visit to our political forums, be sure to check out the RULES. Registering for debate politics is necessary before posting. Register today to participate - it's free!
  • Welcome to our archives. No new posts are allowed here.

Nate Silver-led statistics men crush pundits in election

Let me point out again that Dr. Sam Wang of the Princeton Election Consortium gets far too little credit. He's been more accurate than Silver in the past, and this time he picked the national vote count to the decimal (51.1% - 48.9%). He was 10 for 10 in Senate races (one better than Silver), and he will have probably missed the EC by Florida, which he was correct in calling a virtual coin toss.
 
Just to clarify something: what Nate Silver does, and what polls do, are two different things that do not compare well. Polls show a "snapshot in time", with a relatively large margin of error and no conclusions drawn. What Silver does is draw conclusions using a statistical model and an aggregate of polls data(plus other data). One of the advantages that Silver has is a much larger data poll which significantly reduces margin of error.
 
Love it -- the tea party conspiracy theory that Silver was a shill for the libral media. Another discredited talking point shot down by reality

Facts are not the friend of conservatism.
 
Somerville said:
I read it the same as upsideguy at first but I believe Verax was posting in a sarcastic manner and his "pew" was not "Pew"
Click to expand...

.... I was merely making the play on the words... I caught the distinction between pew and Pew, I was just having fun with it.
 
AdamT said:
Let me point out again that Dr. Sam Wang of the Princeton Election Consortium gets far too little credit. He's been more accurate than Silver in the past, and this time he picked the national vote count to the decimal (51.1% - 48.9%). He was 10 for 10 in Senate races (one better than Silver), and he will have probably missed the EC by Florida, which he was correct in calling a virtual coin toss.
Click to expand...

Wang should get plenty of credit. I mostly go to Nate Silver just because I prefer his writing and explanations. He is better at presenting in my opinion and explaining.
 
roughdraft274 said:
Wang should get plenty of credit. I mostly go to Nate Silver just because I prefer his writing and explanations. He is better at presenting in my opinion and explaining.
Click to expand...

I agree, and I think that's why Silver gets most of the intention. He's more prolific and he's very good at putting things in laymens' terms.
 
Silver is remarkable. His blog analysis last night was spot on.

Where are all the knownothing conservatives and their libral media conspiracy theories today? They need a new narrative, which I think is: Romney wasn't conservative enough. BWHAHHAHAHAHHAHAHH!
 
StillBallin75 said:
Analyses from guys like Silver provide a set of probabilities, and if you look closely he was slightly off on the electoral vote count (He predicted 313-225 Obama).
Click to expand...
No. That was the average of all outcomes. If you look at the discrete outcome graph, down near the bottom of the forecast, there were 3 peaks. The second highest peak was 303 EV (where it is now) and the highest peak, at 20% likelihood, was 332 (where it will be if FL does indeed get called blue).

XKCD said it best: Math
 
Wiseone said:
No one wants to watch math on TV.
Click to expand...
That's only because we haven't found a way to make math on TV interesting. But Nate Silver's blog accounted for, I think, 20% of the NYT's traffic yesterday and people were pretty interested in that story. In my opinion, I think mathematical and other academic thinking aren't popular because people just haven't applied enough creative energy to make it interesting.
 
GOP will make gains in 2 years most likely. It'll be a mid-term election where voter turnout is lower. They do better there.
 
roughdraft274 said:
Nate Silver was one of the many reasons I wasn't terribly worried about this election.

Is he going to be 100%? nope, but so far, in every single election he has predicted, and every state he has predicted, if he claims a confidence interval over 60%, he has 100% accuracy.
Click to expand...

He did get a couple Senate races wrong though. He predicted Democrats would lose the Senate race in Montana (with a 65.6% probability) and in North Dakota (with a 92.5% probability)...but it looks like the Democrats will win both. In both cases he was "wrong," although as Nate himself as quick to point out, we should *expect* 90% favorites to lose about 10% of the time.
 
You must log in or register to reply here.
Back
Top Bottom