Nate Silver vs Intrade in Iowa
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
May 31, 2024, 10:49:43 PM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2012 Elections
  Nate Silver vs Intrade in Iowa
« previous next »
Pages: [1]
Poll
Question: which set of odds-to-win-IA do you think best corresponds to the reality?
#1
Romney 50.5 | Paul 25.9 | Santorum 21.6
 
#2
Romney 63 | Paul 21 | Santorum 12
 
Show Pie Chart
Partisan results

Total Voters: 40

Author Topic: Nate Silver vs Intrade in Iowa  (Read 1602 times)
© tweed
Miamiu1027
Atlas Superstar
*****
Posts: 36,562
United States


Show only this user's posts in this thread
« on: January 01, 2012, 08:38:19 AM »

.
Logged
Antonio the Sixth
Antonio V
Atlas Institution
*****
Posts: 58,351
United States


Political Matrix
E: -7.87, S: -3.83

P P
Show only this user's posts in this thread
« Reply #1 on: January 01, 2012, 09:27:07 AM »

I like Nate and he often outperforms everybody when it comes to electoral predictions, but this time I really think his forecast model is hugely overconfident.
Logged
© tweed
Miamiu1027
Atlas Superstar
*****
Posts: 36,562
United States


Show only this user's posts in this thread
« Reply #2 on: January 01, 2012, 10:27:08 AM »

I like Nate and he often outperforms everybody when it comes to electoral predictions, but this time I really think his forecast model is hugely overconfident.

models are not self-aware.  Silver himself has commented that he believes the Romney number too high and Santorum too low.
Logged
Antonio the Sixth
Antonio V
Atlas Institution
*****
Posts: 58,351
United States


Political Matrix
E: -7.87, S: -3.83

P P
Show only this user's posts in this thread
« Reply #3 on: January 01, 2012, 12:48:51 PM »

I like Nate and he often outperforms everybody when it comes to electoral predictions, but this time I really think his forecast model is hugely overconfident.

models are not self-aware.  Silver himself has commented that he believes the Romney number too high and Santorum too low.

Is this thread about the forecasted odds or about Nate's gut feeling ?
Logged
© tweed
Miamiu1027
Atlas Superstar
*****
Posts: 36,562
United States


Show only this user's posts in this thread
« Reply #4 on: January 01, 2012, 02:24:30 PM »

I like Nate and he often outperforms everybody when it comes to electoral predictions, but this time I really think his forecast model is hugely overconfident.

models are not self-aware.  Silver himself has commented that he believes the Romney number too high and Santorum too low.

Is this thread about the forecasted odds or about Nate's gut feeling ?

forecasted
Logged
TheGlobalizer
Sr. Member
****
Posts: 3,286
United States


Political Matrix
E: 6.84, S: -7.13

Show only this user's posts in this thread
« Reply #5 on: January 01, 2012, 02:33:26 PM »

Intrade, by far.  I think they still overvalue Romney, his support is soft, easier to get over the phone than in an hours-long caucus.

Not a fan of Nate Silver.
Logged
© tweed
Miamiu1027
Atlas Superstar
*****
Posts: 36,562
United States


Show only this user's posts in this thread
« Reply #6 on: January 01, 2012, 02:35:02 PM »


that's a shame, you should be
Logged
TheGlobalizer
Sr. Member
****
Posts: 3,286
United States


Political Matrix
E: 6.84, S: -7.13

Show only this user's posts in this thread
« Reply #7 on: January 01, 2012, 02:38:51 PM »


Too much personal bias in his analysis.  At least there was in 2008; not sure how much he's improved, but moving to NYT doesn't speak particularly well of that notion.
Logged
argentarius
Jr. Member
***
Posts: 843
Ireland, Republic of


Show only this user's posts in this thread
« Reply #8 on: January 01, 2012, 02:43:43 PM »

Intrade, by far.  I think they still overvalue Romney, his support is soft, easier to get over the phone than in an hours-long caucus.

Not a fan of Nate Silver.

I disagree on Romney's support. His support now seems to be even more rock solid than Paul. Whether they're politically active though is different entirely.
Logged
Antonio the Sixth
Antonio V
Atlas Institution
*****
Posts: 58,351
United States


Political Matrix
E: -7.87, S: -3.83

P P
Show only this user's posts in this thread
« Reply #9 on: January 01, 2012, 02:47:04 PM »

I like Nate and he often outperforms everybody when it comes to electoral predictions, but this time I really think his forecast model is hugely overconfident.

models are not self-aware.  Silver himself has commented that he believes the Romney number too high and Santorum too low.

Is this thread about the forecasted odds or about Nate's gut feeling ?

forecasted

So what's your point exactly ?
Logged
© tweed
Miamiu1027
Atlas Superstar
*****
Posts: 36,562
United States


Show only this user's posts in this thread
« Reply #10 on: January 01, 2012, 03:22:50 PM »

that a model cannot be 'overconfident' as it is not self-aware, and that evidence exists to suggest  Nate himself is not overconfident in his model.
Logged
Lief 🗽
Lief
Atlas Legend
*****
Posts: 45,018


Show only this user's posts in this thread
« Reply #11 on: January 01, 2012, 03:25:47 PM »

Romney's not going to win Iowa. I stake my reputation as an ace prognosticator and firm, but caring lover on it.
Logged
Antonio the Sixth
Antonio V
Atlas Institution
*****
Posts: 58,351
United States


Political Matrix
E: -7.87, S: -3.83

P P
Show only this user's posts in this thread
« Reply #12 on: January 01, 2012, 03:42:50 PM »

that a model cannot be 'overconfident' as it is not self-aware, and that evidence exists to suggest  Nate himself is not overconfident in his model.

Seriously, I can't believe you actually didn't get it. By "overconfident" I obviously meant it overestimated the frontrunner's likelihood to win.
Logged
Pages: [1]  
« previous next »
Jump to:  


Login with username, password and session length

Terms of Service - DMCA Agent and Policy - Privacy Policy and Cookies

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

Page created in 0.236 seconds with 13 queries.