- My Forums
- Tiger Rant
- LSU Recruiting
- SEC Rant
- Saints Talk
- Pelicans Talk
- More Sports Board
- Fantasy Sports
- Golf Board
- Soccer Board
- O-T Lounge
- Tech Board
- Home/Garden Board
- Outdoor Board
- Health/Fitness Board
- Movie/TV Board
- Book Board
- Music Board
- Political Talk
- Money Talk
- Fark Board
- Gaming Board
- Travel Board
- Food/Drink Board
- Ticket Exchange
- TD Help Board
Customize My Forums- View All Forums
- Show Left Links
- Topic Sort Options
- Trending Topics
- Recent Topics
- Active Topics
Started By
Message
.
Posted on 12/11/17 at 7:05 pm
Posted on 12/11/17 at 7:05 pm
(no message)
This post was edited on 11/9/23 at 11:52 am
Posted on 12/11/17 at 7:15 pm to DelU249
Nate Platinum putting Fox’s poll on notice. He even thinks it’s outlandish
Posted on 12/11/17 at 7:23 pm to idlewatcher
He’s congratulating them for publishing a poll that he finds suspect as shite
Posted on 12/11/17 at 7:32 pm to DelU249
Well, I hate Silver as much as anyone, but he's got a point that publishing "bad" polls is way better than trying to hide them or massage their numbers.
If your polling methodology produces a result that says candidate B is going to win by +10 points and he ends up losing by 10 (a -20 difference) it should come as a huge wake up call that your polling methodology is completely broken.
If your polling methodology produces a result that says candidate B is going to win by +10 points and he ends up losing by 10 (a -20 difference) it should come as a huge wake up call that your polling methodology is completely broken.
Posted on 12/11/17 at 7:38 pm to IAmReality
quote:
he's got a point that publishing "bad" polls is way better than trying to hide them or massage
absolutely. outlier polls are also part of their track record and shouldn't be hidden. hopefully other major polling firms do the same thing
of course, they face a huge upside if gump voters shock everyone and give jones the seat
Posted on 12/11/17 at 7:48 pm to DelU249
You prove you didnt understand his data.
I did.
I kept explaining to the crying td posters that in nates data trump won thousands of times in every series of simulations.
I did.
I kept explaining to the crying td posters that in nates data trump won thousands of times in every series of simulations.
This post was edited on 12/11/17 at 7:49 pm
Posted on 12/11/17 at 9:07 pm to CelticDog
Thousands among how many simulations?
I get it, but it doesn’t change reality. When you say someone has an 80% chance of winning, you’re functionally making a prediction they will win. Since Nate isn’t stupid and relished in being the guy who “predicted” every state in 2012 I’m guessing he knows that. Color me unimpressed that his model accounts for changes like actual voting that isn’t what he predicted.
On a side note, he aggressively defended the polling process while he admits here it may be common for pollsters to throw away results that don’t match their perception of things
I get it, but it doesn’t change reality. When you say someone has an 80% chance of winning, you’re functionally making a prediction they will win. Since Nate isn’t stupid and relished in being the guy who “predicted” every state in 2012 I’m guessing he knows that. Color me unimpressed that his model accounts for changes like actual voting that isn’t what he predicted.
On a side note, he aggressively defended the polling process while he admits here it may be common for pollsters to throw away results that don’t match their perception of things
Posted on 12/11/17 at 9:13 pm to DelU249
He actually has a piece on 538 tonight where he explains why it’s better to publish an outlier poll instead of hiding it. It was a pretty good read. You should check it out.
Posted on 12/11/17 at 9:13 pm to DelU249
n
This post was edited on 7/22/19 at 10:57 am
Posted on 12/11/17 at 9:15 pm to DelU249
quote:
2. Hey, I think this poll sounds screwy and I know it’s a statistical outlier, but KUDOS!!!
They took a poll, they got a result, and they published the result even though they know there's a decent chance they'll be ridiculed for it.
I don't know what problem you have with that, but if it bothers you, you mustn't understand the process and/or purpose of polling. If Nate is right that a lot of polling firms would have sat on this result, that'd be a disservice. If pollsters just make any polls that don't fit their intuition disappear, then there's no point in polling at all.
Posted on 12/11/17 at 9:20 pm to TigersInParis
The pollster isn’t the party catching my attention
The poll will be tested, and shown to be wrong
It’s that Silver is congratulating them and why “congrats on your shitty poll I will totally use and for not throwing it away, others would’ve done that
He answers 2 questions here. Why Nate Silver sucks and why pollsters suck
The poll will be tested, and shown to be wrong
It’s that Silver is congratulating them and why “congrats on your shitty poll I will totally use and for not throwing it away, others would’ve done that
He answers 2 questions here. Why Nate Silver sucks and why pollsters suck
Posted on 12/11/17 at 9:29 pm to DelU249
quote:
Spare me the expected “but he’s assigning probability not making predictions”
Aka spare me the truth.
Posted on 12/11/17 at 9:37 pm to TigerAndBadger
Statisticians who present their results as a prediction are making a prediction
Posted on 12/11/17 at 10:27 pm to DelU249
n
This post was edited on 7/22/19 at 10:57 am
Posted on 12/11/17 at 10:33 pm to TigerAndBadger
quote:
We could emphasize that track record; the methods of data journalism have been highly successful at forecasting elections. That includes quite a bit of success this year. The FiveThirtyEight “polls-only” model has correctly predicted the winner in 52 of 57 (91 percent) primaries and caucuses so far in 2016, and our related “polls-plus” model has gone 51-for-57 (89 percent).
Interesting choice of words
Nate makes predictions...according to Nate
Posted on 12/11/17 at 10:50 pm to CelticDog
I'm so fricking sick of Nate's fanboy defenders.
Do you understand that he looked at every Republican nomination poll during the primaries and still came to the conclusion that Trump had less than 2% chance of winning the nomination?
He compared Trump UNFAVORABLY to Pat Buchanan after he won the NH primaries.
Do you understand that he looked at every Republican nomination poll during the primaries and still came to the conclusion that Trump had less than 2% chance of winning the nomination?
He compared Trump UNFAVORABLY to Pat Buchanan after he won the NH primaries.
Posted on 12/11/17 at 11:05 pm to TigerAndBadger
quote:
That isn't how statistics work. Same way a Baseball player's slugging percentage isn't a prediction of whether he will get a hit or not off a certain pitcher.
ummm, MoneyBall says you're wrong on this
Posted on 12/11/17 at 11:32 pm to SirWinston
Thes fanboys are annoying as shite. Odds makers use probability to make predictions
It’s fricking stupid to pretend otherwise. Nate legend became “nate least wrong”
I got more States right than silver. So really, how useful was his model if I can do a better job with only 5 minutes of abstract thought?
It’s fricking stupid to pretend otherwise. Nate legend became “nate least wrong”
I got more States right than silver. So really, how useful was his model if I can do a better job with only 5 minutes of abstract thought?
Popular
Back to top
Follow TigerDroppings for LSU Football News