Tuesday, October 27, 2020

Nate silver has to be absolutely shitting his pants right now.

 

  The most prestigious law school admissions discussion board in the world.
BackRefresh Options Favorite

Nate silver has to be absolutely shitting his pants right now.

Even if he remains committed to his forecast, there is a 13%...
absolutely devastating for board libs
  10/27/20
Hasnt had credibility since 2016
Queensbridge Wilbur
  10/27/20
Agree but he’s been able to lisp about 30%. If this on...
absolutely devastating for board libs
  10/27/20
Look Nate Plastic is a faggot who I hope gets corncobbed nex...
The Agricultural Revolution and its consequences h
  10/27/20
Lmao which one of us is revising history? Who did he predict...
Queensbridge Wilbur
  10/27/20
The only thing that matters is your predictions relative to ...
The Agricultural Revolution and its consequences h
  10/27/20
The judge ALMOST granted our motion for summary judgment. Yo...
Candy Ride
  10/27/20
He brought it upon himself. He's been really bad about chang...
field & stream subscriber
  10/27/20
It's nuts that his claim to fame is 49/50. Probably 25 or 30...
Candy Ride
  10/27/20
...
,.,...,..,.,.,;:,.:,.,.,::,..,..,:,.,.:.:.,:.::,.
  10/27/20
That's true of every election for him. There's no escaping t...
LathamTouchedMe
  10/27/20
Lol. Nobody pays attention to midterms and they’re mor...
absolutely devastating for board libs
  10/27/20
Midterms are actually harder to predict. More potential for ...
LathamTouchedMe
  10/27/20
Can't he just say Trump got lucky with the 13%?
gibberish
  10/27/20
He already did that with Hillary. Do you know the probabilit...
absolutely devastating for board libs
  10/27/20
390 percent seems high
Orange Team Bad
  10/27/20
Think you’re calculator is broken breh
absolutely devastating for board libs
  10/27/20
...
A Jurisprudence is Performed
  10/27/20
...
David Poaster Wallace
  10/27/20
...
system poaster
  10/27/20
Do all the people blank bumping this think this is not the c...
absolutely devastating for board libs
  10/27/20
you seem to be having a meltdown in this thread lil breh
.,;\'.,;\'.,.;\'.,.;\'.,,.;,;.;,.\'\'\';[;.,,\'
  10/27/20
Nah brej I’m loling at math illiterate lawyers who don...
absolutely devastating for board libs
  10/27/20
i wonder what bumps mean on this chatboard
.,;\'.,;\'.,.;\'.,.;\'.,,.;,;.;,.\'\'\';[;.,,\'
  10/27/20
tbf it’s hard to tell. In 2007 I would’ve assume...
absolutely devastating for board libs
  10/27/20
lol
A Jurisprudence is Performed
  10/27/20
Nah he's right
'"'''"''"''"
  10/27/20
If I'm interpreting this correctly, the math gives Trump thr...
David Poaster Wallace
  10/27/20
...
spritezero
  10/27/20
(Hillary voter)
ass lord (retired)
  10/27/20
...
TheRealGreenJollyRancher
  10/27/20
...
.,,,,,.,....,...,..,,...,..,,,.,..,,,..,,,...
  10/27/20
genuine lol.
.,.,'..,'..,.,.,...
  10/27/20
(mook)
'''''''''''''''''''"'
  10/27/20
...
field & stream subscriber
  10/27/20
50/50 it either happens or it doesn't bro
DrakeMallard
  10/27/20
The problem is that it makes zero sense the way he frames it...
borders
  10/27/20
The problem is that there is no way to actually verify after...
I'm gay tp
  10/27/20
Yeah but you can peg the odds he was “right” abo...
absolutely devastating for board libs
  10/27/20
I don’t think that’s how it works man.
I'm gay tp
  10/27/20
It’s exactly how it works. Do you probability at all?
absolutely devastating for board libs
  10/27/20
That’s not how you determine the odds he was “ri...
I'm gay tp
  10/27/20
(dumb faggot)
'"'''"''"''"
  10/27/20
Ok you so spot him a few points for being wrong that both ev...
absolutely devastating for board libs
  10/27/20
My point is that you can’t actually prove he was wrong...
I'm gay tp
  10/27/20
I’m saying it’s not a sample size or of one, it&...
absolutely devastating for board libs
  10/27/20
You’ve got to be flame. If you bought a powerball t...
I'm gay tp
  10/27/20
Much less likely to be wrong because you (presumably) gave ...
absolutely devastating for board libs
  10/27/20
Wow, this subthread is embarrassing for you. I’ll be n...
I'm gay tp
  10/27/20
You’re right except you have it backwards. State your ...
absolutely devastating for board libs
  10/27/20
You do realize the difference between the lottery ticket and...
I'm gay tp
  10/27/20
Why don’t you help me. If I predict mike trout has a 1...
absolutely devastating for board libs
  10/27/20
If you predicted Trout had a 30% chance of a hit in his firs...
I'm gay tp
  10/27/20
The more often the model predicts events have low probabilit...
absolutely devastating for board libs
  10/27/20
You got completely pwned.
I'm gay tp
  10/27/20
Lol
absolutely devastating for board libs
  10/27/20
You’ve been exposed.
I'm gay tp
  10/27/20
There's a very clear difference there. To use your baseball ...
LathamTouchedMe
  10/27/20
And that doubt disappears more and more over time when the o...
absolutely devastating for board libs
  10/27/20
Do you recognize the difference between n=2 and n=100?
I'm gay tp
  10/27/20
So literally all you’re saying now is that we know mor...
absolutely devastating for board libs
  10/27/20
“Far more probable than not” Show your math ...
I'm gay tp
  10/27/20
I’ve explained this to you thoroughly. If you have a m...
absolutely devastating for board libs
  10/27/20
God you are retarded.
I'm gay tp
  10/27/20
Just gay actually
absolutely devastating for board libs
  10/27/20
dude, c'mon! lol.
LathamTouchedMe
  10/27/20
State your math background.
absolutely devastating for board libs
  10/27/20
Based on your logic, how was Nate Silver any more right than...
Candy Ride
  10/27/20
Hey retard still awaiting your analysis here. Is my model ve...
absolutely devastating for board libs
  10/27/20
I’m working on actual work lol. Will reply.
I'm gay tp
  10/27/20
His argument is that nate's model is not falsifiable. We don...
LathamTouchedMe
  10/27/20
It doesn’t matter that it’s not falsifiable &mda...
absolutely devastating for board libs
  10/27/20
You can’t prove it’s incorrect just because a th...
I'm gay tp
  10/27/20
It’s not about “proving” it’s incorr...
absolutely devastating for board libs
  10/27/20
You can’t make that determination with a n=2. And you ...
I'm gay tp
  10/27/20
Actually you can. Well not exactly you have to add back the ...
absolutely devastating for board libs
  10/27/20
...
+5% discipline
  10/27/20
no, your calculation was meaningless. in reality, that tick...
A Jurisprudence is Performed
  10/27/20
Just jump before the ticket wins.
I'm gay tp
  10/27/20
As to "any given ticket" I guess your calculation ...
A Jurisprudence is Performed
  10/27/20
I think Nate Silver would argue his job is to accurately pre...
I'm gay tp
  10/27/20
There is no point of him giving odds. The point of beyesian ...
Candy Ride
  10/27/20
Why don't you explain you annoying faggot
'"'''"''"''"
  10/27/20
actually he was wrong twice which is 0% HTH
ass lord (retired)
  10/27/20
It's true that you can do this, but it's still incredibly sk...
borders
  10/27/20
is it right in your view to say that what hes doing is selec...
.,.,;,.,..,.,.,:,,:,...,:::,...,:,.,.:...:.,:.::,.
  10/27/20
https://statmodeling.stat.columbia.edu/2020/10/24/reverse-en...
borders
  10/27/20
Everything is fate. Probability is an artificial construct t...
ominous gulp
  10/27/20
it's just useless to model human behavior. works great for e...
ass lord (retired)
  10/27/20
...
A Jurisprudence is Performed
  10/27/20
i remember when libs treated him as the election instead of ...
.,.,,..,..,.,.,:,,:,...,::,....,:,.,.:...:.,:.::,.
  10/27/20
lol no, even if trump won he'd still keep doing his same sht...
system poaster
  10/27/20
...
JohnWinthrop
  10/27/20
...
lsd
  10/27/20
what's his 'model'? just some linear regression?
spritezero
  10/27/20
his model shows that if Trump is within a few points of Rhod...
.,.,.,.,.,...,.,,.,,.....,.,..,.,,...,.,.,,...,.
  10/27/20
And that Trump could win CA but Biden still has a good chanc...
absolutely devastating for board libs
  10/27/20
Nate Silver will suffer zero consequences for being wrong ...
A Jurisprudence is Performed
  10/27/20
...
system poaster
  10/27/20
so much this
dirte
  10/27/20
Donna Brazile too. Multi-time loser as a POTUS campaign mana...
hung stud
  10/27/20
-- and then got hired BY FOX OF ALL PLACES
.,.,'..,'..,.,.,...
  10/27/20
He doesn't have enough of a foothold in either ideological c...
LathamTouchedMe
  10/27/20
Cr. And also the palliative value of a pollster is tied dire...
absolutely devastating for board libs
  10/27/20
What is his ideology? I know he's a climate change skepti...
+5% discipline
  10/27/20
Intuitively I agree with you - but I think we're underestima...
borders
  10/27/20
...
'"'""'"''"
  10/27/20
so true. but i some point i concluded that being wrong ...
.,.,'..,'..,.,.,...
  10/27/20
13% chance turning into 50/50
hung stud
  10/27/20
Why his job is to tell libs what they want to hear
,.,.,.,,...,,.....,,...
  10/27/20
Cr but it will lose its palliative effect if he’s alwa...
absolutely devastating for board libs
  10/27/20
Let's see where his prediction slides on election Eve.
gibberish
  10/27/20
...
self care
  10/27/20
what's his clique?
spritezero
  10/27/20
it's bad. real bad.
A Jurisprudence is Performed
  10/27/20
...
computer fan
  10/27/20
xoxo is so stunningly bad when it comes to statistics, it's ...
Hunter S Biden
  10/27/20
Look out guys, we have a STATISTICIAN here!
;..;.;;;.;;.;.;.;;;.;;;.;.;;;....;.
  10/27/20
math major and former stats teacher here care to elabora...
oneforthethumb
  10/27/20
...
'"'""'"'''""
  10/27/20
just do punditry and say everything is a 50/50 chance, bro
commacommadotdotcomma
  10/27/20
Nate Silver is a fucking FRAUD. Barnes is on it. Silver...
oneforthethumb
  10/27/20
nah dude its all good check out this infographic no way some...
.,.,;,.,..,.,.,:,,:,...,:::,...,:,.,.:...:.,:.::,.
  10/27/20
cr
propagandist
  10/27/20
It's true that you can do this, but it's still incredibly sk...
borders
  10/27/20
thank you 🙏
oneforthethumb
  10/27/20
Real q: what is the point of him hiding that ball this way? ...
absolutely devastating for board libs
  10/27/20
he's a charlatan
.,.,.,.,.,...,.,,.,,.....,.,..,.,,...,.,.,,...,.
  10/27/20
Don't get me wrong, it's not completely obvious how we *shou...
borders
  10/27/20
How was he supposed to predict putin would hack the election...
gibberish
  10/27/20
Cr. He's probably nervous about the election results too
cornbread
  10/27/20
...
reckless monkey in a tropical forest
  10/27/20
...
'"'""'"''"
  10/27/20
...
absolutely devastating for board libs
  10/27/20
...
propagandist
  10/27/20
I’ve been a Long time listener to his podcast. He&rsqu...
.....................:......:::.......;...........
  10/27/20


 Poast new message in this thread



 ReplyFavorite

Date: October 27th, 2020 3:16 PM
Author: absolutely devastating for board libs

Even if he remains committed to his forecast, there is a 13% chance his credibility is completely shot. And deep down he knows it’s higher.

Nobody is going to care about any of his lisping or details about how akshually i gave him a 13% chance after the fact if Trump wins, given Hillary. He is all in and he knows it.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198675)



  ReplyFavorite

Date: October 27th, 2020 3:18 PM
Author: Queensbridge Wilbur (Krugerrand)

Hasnt had credibility since 2016

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198686)



  ReplyFavorite

Date: October 27th, 2020 3:19 PM
Author: absolutely devastating for board libs

Agree but he’s been able to lisp about 30%. If this one is 12% and Biden loses its over over

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198696)



  ReplyFavorite

Date: October 27th, 2020 3:34 PM
Author: The Agricultural Revolution and its consequences h

Look Nate Plastic is a faggot who I hope gets corncobbed next week but let's not revise history. He actually made the "markets" his bitch in the 2016 general election. Bookmakers had implied odds of ~15% for Trump the morning of the election. He also stood firm in the face of liberal media outlets forecasting 99% and talking shit on him for having Trump too high.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198839)



  ReplyFavorite

Date: October 27th, 2020 5:10 PM
Author: Queensbridge Wilbur (Krugerrand)

Lmao which one of us is revising history? Who did he predict was going to win?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199666)



  ReplyFavorite

Date: October 27th, 2020 5:24 PM
Author: The Agricultural Revolution and its consequences h

The only thing that matters is your predictions relative to the market. Nate destroyed the market in 2016. He should gain credibility for his performance in the 2016 general

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199802)



  ReplyFavorite

Date: October 27th, 2020 8:19 PM
Author: Candy Ride

The judge ALMOST granted our motion for summary judgment. You should applaud me, client.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200872)



  ReplyFavorite

Date: October 27th, 2020 3:21 PM
Author: field & stream subscriber

He brought it upon himself. He's been really bad about changing his model on the fly once it stops making sense, but now I think he has nowhere to run. It's been nearly a decade since he "called 49/50 states"

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198713)



  ReplyFavorite

Date: October 27th, 2020 8:20 PM
Author: Candy Ride

It's nuts that his claim to fame is 49/50. Probably 25 or 30 percent of poasters can do that each election.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200882)



  ReplyFavorite

Date: October 27th, 2020 3:24 PM
Author: ,.,...,..,.,.,;:,.:,.,.,::,..,..,:,.,.:.:.,:.::,.




(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198747)



  ReplyFavorite

Date: October 27th, 2020 3:27 PM
Author: LathamTouchedMe

That's true of every election for him. There's no escaping the nature of his business. He probably had the same feeling before the 2018 election. A bad call there and it would have been two in a row.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198767)



  ReplyFavorite

Date: October 27th, 2020 3:29 PM
Author: absolutely devastating for board libs

Lol. Nobody pays attention to midterms and they’re more predictable since only hardcore voters vote. To repeat: no one gives a fuck about 2018 - Nate is all in now to redeem 2016 and he knows it.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198788)



  ReplyFavorite

Date: October 27th, 2020 3:35 PM
Author: LathamTouchedMe

Midterms are actually harder to predict. More potential for polling misses. And yes, 2018 mattered in that he had to get it right. No one would even be paying attention to polls or his model if he whiffed in 2018.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198842)



  ReplyFavorite

Date: October 27th, 2020 3:30 PM
Author: gibberish

Can't he just say Trump got lucky with the 13%?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198799)



  ReplyFavorite

Date: October 27th, 2020 3:32 PM
Author: absolutely devastating for board libs

He already did that with Hillary. Do you know the probability of a 30% chance event being followed by a 13% chance event?

Hint: multiply 30% x 13%.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198812)



  ReplyFavorite

Date: October 27th, 2020 3:33 PM
Author: Orange Team Bad

390 percent seems high

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198827)



  ReplyFavorite

Date: October 27th, 2020 3:34 PM
Author: absolutely devastating for board libs

Think you’re calculator is broken breh

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198838)



  ReplyFavorite

Date: October 27th, 2020 3:35 PM
Author: A Jurisprudence is Performed



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198853)



  ReplyFavorite

Date: October 27th, 2020 3:39 PM
Author: David Poaster Wallace



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198886)



  ReplyFavorite

Date: October 27th, 2020 3:42 PM
Author: system poaster



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198918)



  ReplyFavorite

Date: October 27th, 2020 3:46 PM
Author: absolutely devastating for board libs

Do all the people blank bumping this think this is not the correct math? Are you all stupid?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198953)



  ReplyFavorite

Date: October 27th, 2020 3:47 PM
Author: .,;\'.,;\'.,.;\'.,.;\'.,,.;,;.;,.\'\'\';[;.,,\'


you seem to be having a meltdown in this thread lil breh

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198967)



  ReplyFavorite

Date: October 27th, 2020 3:48 PM
Author: absolutely devastating for board libs

Nah brej I’m loling at math illiterate lawyers who don’t know math bumping eAch others wrong math. It’s lulzy.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198978)



  ReplyFavorite

Date: October 27th, 2020 3:52 PM
Author: .,;\'.,;\'.,.;\'.,.;\'.,,.;,;.;,.\'\'\';[;.,,\'


i wonder what bumps mean on this chatboard

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199009)



  ReplyFavorite

Date: October 27th, 2020 3:55 PM
Author: absolutely devastating for board libs

tbf it’s hard to tell. In 2007 I would’ve assumed it was a joke but in 2020 most of xo is fully retarded. At least some of these blankbumps are morons for sure

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199039)



  ReplyFavorite

Date: October 27th, 2020 3:52 PM
Author: A Jurisprudence is Performed

lol

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199011)



  ReplyFavorite

Date: October 27th, 2020 3:49 PM
Author: '"'''"''"''"

Nah he's right

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198986)



  ReplyFavorite

Date: October 27th, 2020 4:55 PM
Author: David Poaster Wallace

If I'm interpreting this correctly, the math gives Trump three terms with a 90% of a 4th

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199540)



  ReplyFavorite

Date: October 27th, 2020 4:16 PM
Author: spritezero



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199201)



  ReplyFavorite

Date: October 27th, 2020 4:27 PM
Author: ass lord (retired)

(Hillary voter)

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199311)



  ReplyFavorite

Date: October 27th, 2020 4:38 PM
Author: TheRealGreenJollyRancher



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199414)



  ReplyFavorite

Date: October 27th, 2020 5:08 PM
Author: .,,,,,.,....,...,..,,...,..,,,.,..,,,..,,,...




(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199648)



  ReplyFavorite

Date: October 27th, 2020 5:15 PM
Author: .,.,'..,'..,.,.,...

genuine lol.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199702)



  ReplyFavorite

Date: October 27th, 2020 5:57 PM
Author: '''''''''''''''''''"'

(mook)

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200090)



  ReplyFavorite

Date: October 27th, 2020 9:20 PM
Author: field & stream subscriber



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41201402)



  ReplyFavorite

Date: October 27th, 2020 3:47 PM
Author: DrakeMallard

50/50 it either happens or it doesn't bro

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198960)



  ReplyFavorite

Date: October 27th, 2020 5:17 PM
Author: borders

The problem is that it makes zero sense the way he frames it for his low info audience to understand

A Trump win is not a "15% event happening" , it's not like oh wow we drew a jack of spades what are the odds! Or that it's some stochastic mechanism like a 'random' drawing of a lottery ball, and a low chance event just occurred

Narrating as such to his readers is betraying his own favored philosophy for analysis - bayesian - where it represents a degree of belief in an event occurring, and you update those beliefs by incorporating new data/ info into your set of information

A better analogy would be his model is a measurement device, and it's too low resolution

A Trump victory occurring just puts reality into higher resolution for everyone to see

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199724)



  ReplyFavorite

Date: October 27th, 2020 3:35 PM
Author: I'm gay tp

The problem is that there is no way to actually verify after the fact that Trump really had a 13% chance or a 50% or 75% chance. It’s all just made up bullshit.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198845)



  ReplyFavorite

Date: October 27th, 2020 3:36 PM
Author: absolutely devastating for board libs

Yeah but you can peg the odds he was “right” about 30% followed by 13% very easily.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198860)



  ReplyFavorite

Date: October 27th, 2020 3:38 PM
Author: I'm gay tp

I don’t think that’s how it works man.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198876)



  ReplyFavorite

Date: October 27th, 2020 3:39 PM
Author: absolutely devastating for board libs

It’s exactly how it works. Do you probability at all?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198887)



  ReplyFavorite

Date: October 27th, 2020 3:42 PM
Author: I'm gay tp

That’s not how you determine the odds he was “right”

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198913)



  ReplyFavorite

Date: October 27th, 2020 3:42 PM
Author: '"'''"''"''"

(dumb faggot)

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198923)



  ReplyFavorite

Date: October 27th, 2020 3:44 PM
Author: absolutely devastating for board libs

Ok you so spot him a few points for being wrong that both events were even LESS likely than he said. Without actually doing the math that’s, what, up to 6% chance his models were “right”?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198938)



  ReplyFavorite

Date: October 27th, 2020 3:57 PM
Author: I'm gay tp

My point is that you can’t actually prove he was wrong about 2016 because it’s a sample size of one. If I put together some model to predict the odds of a team winning a football game. You run the model for enough games and you eventually have enough of a sample size to prove or disprove that the model works.

If you lived in a world with access to perfect information, you could probably build some sort of model to accurately predict the election with 100% confidence. But polls and all of the information we have are imperfect, so in the real world you can only ever come up with a probability. I’ve only ever argued that Nate Silver’s whole thing is pointless because it’s not falsifiable.

But theoretically, if you somehow did come up with a model that did accurately came up with the correct odds based on all available information and it came out to trump having a 6% chance of winning two terms, then Trump actually winning two terms wouldn’t prove the model was wrong. The Bears won 10 coin tosses in a row last season—-unlikely shit happens.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199069)



  ReplyFavorite

Date: October 27th, 2020 4:01 PM
Author: absolutely devastating for board libs

I’m saying it’s not a sample size or of one, it’s a sample size of 2 and it’s very easy to predict the odds of a 30% event followed by a 12-13% event happening. After 2016 Nate could say a 30% chance doesn’t necessarily mean his model was wrong. 30% isn’t that low of a probability. But that followed by a 12-13% chance means he’s very, very likely wrong. Yeah it’s not fore sure but it’s extremely probable. That’s all anything ever is. If Joe Biden shit his pants in public tomorrow it would “probably” be bad for his campaign but somewhere in the multiverse there a tiny probability everyone would feel more sorry for him.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199106)



  ReplyFavorite

Date: October 27th, 2020 4:05 PM
Author: I'm gay tp

You’ve got to be flame.

If you bought a powerball ticket and I told you that you had a 99.99999% chance of losing. If you ended up winning, would that mean that my calculation was wrong?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199137)



  ReplyFavorite

Date: October 27th, 2020 4:08 PM
Author: absolutely devastating for board libs

Much less likely to be wrong because you (presumably) gave me the same odds as everyone else and 99.99999% of them did lose. That’s not so here.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199156)



  ReplyFavorite

Date: October 27th, 2020 4:11 PM
Author: I'm gay tp

Wow, this subthread is embarrassing for you. I’ll be nice and let you blank your poasts.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199171)



  ReplyFavorite

Date: October 27th, 2020 4:12 PM
Author: absolutely devastating for board libs

You’re right except you have it backwards. State your math background.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199179)



  ReplyFavorite

Date: October 27th, 2020 4:15 PM
Author: I'm gay tp

You do realize the difference between the lottery ticket and example and the election model, right?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199198)



  ReplyFavorite

Date: October 27th, 2020 4:21 PM
Author: absolutely devastating for board libs

Why don’t you help me. If I predict mike trout has a 1% chance of getting a hit every time he walks up to the plate and he bats .300 on the season my hitting model is unfalsifiable so I can’t be wrong, correct?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199248)



  ReplyFavorite

Date: October 27th, 2020 4:45 PM
Author: I'm gay tp

If you predicted Trout had a 30% chance of a hit in his first at bat and a 13% chance of a hit in his second at bat and he went 2-2, could you confidently say the model was wrong?



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199465)



  ReplyFavorite

Date: October 27th, 2020 4:58 PM
Author: absolutely devastating for board libs

The more often the model predicts events have low probability and they occur the more likely it’s incorrect, yes.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199567)



  ReplyFavorite

Date: October 27th, 2020 4:59 PM
Author: I'm gay tp

You got completely pwned.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199572)



  ReplyFavorite

Date: October 27th, 2020 5:02 PM
Author: absolutely devastating for board libs

Lol

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199598)



  ReplyFavorite

Date: October 27th, 2020 5:10 PM
Author: I'm gay tp

You’ve been exposed.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199660)



  ReplyFavorite

Date: October 27th, 2020 4:46 PM
Author: LathamTouchedMe

There's a very clear difference there. To use your baseball example, Silver's model is like saying trout has a 30% chance of getting a hit at his next at bat. That's it! Nate's model doesn't go any further than that. So if Trout hits a single, we're sitting here wondering "well, was Nate right?" That's what the poster above is explaining to you.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199469)



  ReplyFavorite

Date: October 27th, 2020 4:56 PM
Author: absolutely devastating for board libs

And that doubt disappears more and more over time when the odds he was correct get lower and lower. At the extreme - over hundreds of at bats. At the less extreme - over two elections, not one, if he’s wrong again. Which is the whole point.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199547)



  ReplyFavorite

Date: October 27th, 2020 4:58 PM
Author: I'm gay tp

Do you recognize the difference between n=2 and n=100?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199563)



  ReplyFavorite

Date: October 27th, 2020 5:02 PM
Author: absolutely devastating for board libs

So literally all you’re saying now is that we know more after 100 than 2? So you’ve had no point all along and you agree with me entirely. Ok then. It’s far more probable nate’s model is wrong than not when you only have 2 Trump elections to go on. And if all you had to go on with mike trout was two at bats where he struck out, no previous career, and you said he would probably bat 300 you’d be likely wrong too.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199595)



  ReplyFavorite

Date: October 27th, 2020 5:07 PM
Author: I'm gay tp

“Far more probable than not”

Show your math here. This is a completely baseless assumption otherwise.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199637)



  ReplyFavorite

Date: October 27th, 2020 5:16 PM
Author: absolutely devastating for board libs

I’ve explained this to you thoroughly. If you have a model that says there’s a 30% chance the market goes down on day 1, and it does, and then on day 2 says there’s a 12-13% chance it goes down, and it does, and that’s your data set, and you don’t get how this shows there’s very likely something up with your model i can’t help you. Invest away.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199716)



  ReplyFavorite

Date: October 27th, 2020 5:22 PM
Author: I'm gay tp

God you are retarded.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199778)



  ReplyFavorite

Date: October 27th, 2020 5:23 PM
Author: absolutely devastating for board libs

Just gay actually

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199791)



  ReplyFavorite

Date: October 27th, 2020 4:58 PM
Author: LathamTouchedMe

dude, c'mon! lol.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199568)



  ReplyFavorite

Date: October 27th, 2020 5:03 PM
Author: absolutely devastating for board libs

State your math background.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199604)



  ReplyFavorite

Date: October 27th, 2020 8:27 PM
Author: Candy Ride

Based on your logic, how was Nate Silver any more right than the people who said Trump had a 1 percent chance?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200936)



  ReplyFavorite

Date: October 27th, 2020 4:38 PM
Author: absolutely devastating for board libs

Hey retard still awaiting your analysis here. Is my model very probably wrong even if it’s not “falsifiable” or not? Need your help here man. You’re a smart guy.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199408)



  ReplyFavorite

Date: October 27th, 2020 4:40 PM
Author: I'm gay tp

I’m working on actual work lol. Will reply.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199431)



  ReplyFavorite

Date: October 27th, 2020 4:22 PM
Author: LathamTouchedMe

His argument is that nate's model is not falsifiable. We don't run the election a million times and see how many times trump won. In the lotto ticket example, we can see how many winners and losers there are. I understand what you're saying though. His model looks pointless to your average reader if reality keeps spitting outcomes that were what his model deemed a low probability event. We can't say his model is wrong, but it seems even more pointless than it is.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199262)



  ReplyFavorite

Date: October 27th, 2020 4:24 PM
Author: absolutely devastating for board libs

It doesn’t matter that it’s not falsifiable — it’s not just “pointless” it’s very probably wrong.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199287)



  ReplyFavorite

Date: October 27th, 2020 4:52 PM
Author: I'm gay tp

You can’t prove it’s incorrect just because a thing with a predicted 6% chance of happening actually happened.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199508)



  ReplyFavorite

Date: October 27th, 2020 4:56 PM
Author: absolutely devastating for board libs

It’s not about “proving” it’s incorrect it’s about shoeing that it’s very PROBABLY incorrect.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199553)



  ReplyFavorite

Date: October 27th, 2020 4:59 PM
Author: I'm gay tp

You can’t make that determination with a n=2. And you certainly don’t calculate the odds his model is probably incorrect by multiplying .3 x .13

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199569)



  ReplyFavorite

Date: October 27th, 2020 5:03 PM
Author: absolutely devastating for board libs

Actually you can. Well not exactly you have to add back the probability the eventuality both outcomes were even less likely.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199609)



  ReplyFavorite

Date: October 27th, 2020 4:09 PM
Author: +5% discipline



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199159)



  ReplyFavorite

Date: October 27th, 2020 4:11 PM
Author: A Jurisprudence is Performed

no, your calculation was meaningless. in reality, that ticket had a 100% chance of winning (it was the winning ticket).

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199166)



  ReplyFavorite

Date: October 27th, 2020 4:13 PM
Author: I'm gay tp

Just jump before the ticket wins.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199180)



  ReplyFavorite

Date: October 27th, 2020 4:17 PM
Author: A Jurisprudence is Performed

As to "any given ticket" I guess your calculation was right, but as to that ticket it was wrong. and if it's you're job to correctly pick lottery ticket winners (to stretch the metaphor) then you've failed.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199213)



  ReplyFavorite

Date: October 27th, 2020 4:23 PM
Author: I'm gay tp

I think Nate Silver would argue his job is to accurately predict the odds, not the winner. Like I’ve said from the beginning, it’s a pointless exercise because it’s impossible to know whether his model was actually right. A low probability event itself is not proof that the odds were wrong.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199275)



  ReplyFavorite

Date: October 27th, 2020 9:00 PM
Author: Candy Ride

There is no point of him giving odds. The point of beyesian probability is to pick winners.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41201208)



  ReplyFavorite

Date: October 27th, 2020 3:42 PM
Author: '"'''"''"''"

Why don't you explain you annoying faggot

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198914)



  ReplyFavorite

Date: October 27th, 2020 4:28 PM
Author: ass lord (retired)

actually he was wrong twice which is 0% HTH

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199319)



  ReplyFavorite

Date: October 27th, 2020 5:30 PM
Author: borders

It's true that you can do this, but it's still incredibly sketchy b/c it's still very dishonest the way he presents it

The validation he provides on his "predictions" aren't actually predictions at all - if you look at what he puts out - it will be like "out of events our model predicted would come true with at least 0.8 probability, 87% of the time these events actually did come true"

This is very deceptive presenting this as validation - another way to translate what I just said was "out of events that were overwhelmingly obvious they would come true, 87% of the time they actually came true"

He's only validating a high threshold of precision which actually excludes a huge set of events in that field

What it doesn't tell you is "out of all events that actually came true, what % of these events did our model *predict* would come true"?

The reason he doesn't give this is why Taleb / anyone w/ statistical training and balls enough to speak out publicly against him (small set of ppl in the world) have criticized him relentlessly - b/c all he's doing is what i said originally , he's not actually willing to make *predictions* by giving a decision boundary on the model in the form of a threshold for the probability , implicitly 0.5 but by no means does it have to be 0.5, by which to say above this threshold the event is predicted yes/true, below is predicted no/false - doing this would allow actual validation as to the quality of his models, and it's not surprising the article we saw the other day showing using his model loses 6% over going w/ long-odds in soccer matches using his soccer predictions - ie one of the areas he CAN be validated in is his soccer model b/c it outputs expected goals, and it gives you a return of -6% against long-odds from that site that wrote the article

What he's doing when he puts out "validation" is he's cranking up the threshold to 0.9, restricting the validation set to only events that are easy to predict instead of all events, and saying "every time our model predicted the Dodgers would beat the Pirates, the dodgers won 94% of those games"

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199860)



  ReplyFavorite

Date: October 27th, 2020 5:33 PM
Author: .,.,;,.,..,.,.,:,,:,...,:::,...,:,.,.:...:.,:.::,.


is it right in your view to say that what hes doing is selecting from the space of all possible combinations of say 100 degrees of freedom the combinations that contains events he thinks are likely, and then reporting the number of times biden wins vs trump in that pre-selected set? this seems absolutely dumb as hell

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199893)



  ReplyFavorite

Date: October 27th, 2020 6:03 PM
Author: borders

https://statmodeling.stat.columbia.edu/2020/10/24/reverse-engineering-the-problematic-tail-behavior-of-the-fivethirtyeight-presidential-election-forecast/

Yeah that's more or less what's happening - and as you point out the degrees of freedom restriction that small ends up w/ some weird stuff - but it's all ultimately proprietary so nobody really knows , but what's especially puzzling b/c one of the largest benefits of Bayesian models are the transparency and flexibility to specify variance components , and incorporate outside information into the model

if you read through this and skim the comments especially, he definitely has some explaining to do when the basic mechanics of his model work like this....

As has been pointed out - he ends up with situations like Trump winning CA but only having 44% chance of winning the election , similarly w/ Biden taking alabama, or biden having greater chance of winning Alaska than trump of HOLDING MI, or Washington state being negatively correlated w/ Alabama

Or trump winning new jersey makes his chance of winning Alaska 58%, wtf?

The article I linked is a 100% must read IMO

What jumps out to me is Gelman showing how low the between state correlations are, translating to some weird ass tail behavior like trump winning CA but losing election

There's all kinds of weird artifacts - Gelman is being polite and asking "whether i had an error in my code" - you have to read between the lines of this article in our current environment of lib groupthink, this article translates to something more like a bomb than a polite inquiry once you adjust for that

Most suspiciously - Gelman brings up how low the between state correlations are, often being negative! weird tail behavior, and too weak of correlation even in the center - why is this significant? Well it's suspect as hell for the exact reason we're in right now - it's becoming more and more clear that Trump's chances of winning FL are way higher than anybody thought , and if we were to be told right now Trump wins FL, I think most of us would place Trump at > 0.5 to win the election..... So it's suspicious that in a year where we might have information like this on a state like FL b/c of expanded EV - that his model is behaving like this, that his statements to gelman make little sense, etc, it's suspicious b/c his model doesn't have to move any even if say FL looks DISASTROUS for Biden.

What it looks like to me in the media / pollsters etc - is that all bets are off this year - and they'll risk anything to suppress counter-narratives so they can basically suppress turnout on the right making ppl think it's over - which obvious won't work b/c they don't monopolize media modes like they used to.

But the article and comments are a must read IMO

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200129)



  ReplyFavorite

Date: October 27th, 2020 4:13 PM
Author: ominous gulp (Poasts are exclusively artistic expression)

Everything is fate. Probability is an artificial construct that we use to quantify what we don’t know.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199182)



  ReplyFavorite

Date: October 27th, 2020 4:28 PM
Author: ass lord (retired)

it's just useless to model human behavior. works great for everything else

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199324)



  ReplyFavorite

Date: October 27th, 2020 4:35 PM
Author: A Jurisprudence is Performed



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199389)



  ReplyFavorite

Date: October 27th, 2020 3:31 PM
Author: .,.,,..,..,.,.,:,,:,...,::,....,:,.,.:...:.,:.::,.


i remember when libs treated him as the election instead of the actual election

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198807)



  ReplyFavorite

Date: October 27th, 2020 3:32 PM
Author: system poaster

lol no, even if trump won he'd still keep doing his same shtick and libs would still worship him as the gold standard of "objectivity." absolutely nothing would change

you still don't get it man

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198816)



  ReplyFavorite

Date: October 27th, 2020 3:39 PM
Author: JohnWinthrop



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198889)



  ReplyFavorite

Date: October 27th, 2020 3:55 PM
Author: lsd (literal autist)



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199045)



  ReplyFavorite

Date: October 27th, 2020 3:33 PM
Author: spritezero

what's his 'model'? just some linear regression?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198822)



  ReplyFavorite

Date: October 27th, 2020 3:34 PM
Author: .,.,.,.,.,...,.,,.,,.....,.,..,.,,...,.,.,,...,.


his model shows that if Trump is within a few points of Rhode Island, Trump is losing Mississippi and South Dakota

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198836)



  ReplyFavorite

Date: October 27th, 2020 3:35 PM
Author: absolutely devastating for board libs

And that Trump could win CA but Biden still has a good chance of winning nationally.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198851)



  ReplyFavorite

Date: October 27th, 2020 3:35 PM
Author: A Jurisprudence is Performed

Nate Silver will suffer zero consequences for being wrong

one of the fascinating aspects of American punditry is that you can be wrong again and again and AGAIN and it doesn't matter. witness the Lincoln Project faggots all of whom, in a just world, would be in federal prison. Instead they are milking out million$

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198849)



  ReplyFavorite

Date: October 27th, 2020 3:41 PM
Author: system poaster



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198902)



  ReplyFavorite

Date: October 27th, 2020 3:43 PM
Author: dirte

so much this

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198929)



  ReplyFavorite

Date: October 27th, 2020 3:45 PM
Author: hung stud

Donna Brazile too. Multi-time loser as a POTUS campaign manager/DNC leader --> multi millionaire "strategist" and hack leaker of debate questions

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198948)



  ReplyFavorite

Date: October 27th, 2020 5:14 PM
Author: .,.,'..,'..,.,.,...

-- and then got hired BY FOX OF ALL PLACES

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199696)



  ReplyFavorite

Date: October 27th, 2020 4:02 PM
Author: LathamTouchedMe

He doesn't have enough of a foothold in either ideological camp to play that game. The few times he's talked about his own political leanings, he's drawn fire from the left. He's not some popular talk-show host, gifted writer, or exciting ideological firebrand. If polling fails this election then he's done; maybe a frank luntz future at best.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199107)



  ReplyFavorite

Date: October 27th, 2020 4:06 PM
Author: absolutely devastating for board libs

Cr. And also the palliative value of a pollster is tied directly to his credibility. He can’t assuage fears if he’s primarily in the business of making predictions that are wrong.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199144)



  ReplyFavorite

Date: October 27th, 2020 4:12 PM
Author: +5% discipline

What is his ideology?

I know he's a climate change skeptic (insofar as libs blame EVERYTHING from hurricanes, floods, and fires on "climate change," with no evidence of causation). Where else does he stray from liberal orthodoxy?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199178)



  ReplyFavorite

Date: October 27th, 2020 5:45 PM
Author: borders

Intuitively I agree with you - but I think we're underestimating his ability to walk back the model as we get closer to election day and it gets higher resolution what will actually happen

If he really sticks to his guns / polls hardcore, I think you're right, mostly b/c his main purpose being served right now is *therapeutic*, not analytic. Take a trip through his website comments or twitter comments - it's like a cult, anybody trying to debate him in there they literally regurgitate his talking points, and you can tell they're heavily coping. Of course we all do that to some degree - but the level of certainty and how much they lionize him is obvious that they're needing to believe he's right to extremes way beyond what any of us would need to.

Anything can happen, but he can just as easily walk back the predictions, blame bad polling, explain it as "low probability event just like i said was possible, etc" - part of me thinks this is possible, part thinks *no fucking way* he gets away w/ that this time given how furious ppl would be w/ him for false belief if Trump ends up winning

It's hard to tell what'll happen - our arguments about polling aside, we also shouldn't underestimate the gatekeeping effect. Part of what they talk about on the PPD webcast is that despite having a clear track record of outperforming literally every single pollster out there, aggregators, left-leaning polls, right-leaning polls etc - the polling 'establishment' refuses to include PPD, or even engage with them / return their calls. He's definitely a Trumpmo - but in 2018 he predicted DeSantis and gosh what was the other upset, while at the same time telling Republicans they're overestimating their house performances and he wasn't getting the results ras / trafalgar etc were getting in the house - even sounding the alarm early in the night when it looked like Dems would massively underperform all around he said no by the early results he could tell.

I think his audience will blow up after being right and he'll get more funding (he's funded by small donations of followers) - but Baris will not get the official creds needed to be considered a "serious" pollster by Silver/Wasserman/Cohen etc, regardless of how well he performs....



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200002)



  ReplyFavorite

Date: October 27th, 2020 4:14 PM
Author: '"'""'"''"



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199183)



  ReplyFavorite

Date: October 27th, 2020 5:13 PM
Author: .,.,'..,'..,.,.,...

so true.

but i some point i concluded that being wrong over and over is the price of admission to the elite-insider game. it's how to show that you will do the necessary work.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199692)



  ReplyFavorite

Date: October 27th, 2020 3:36 PM
Author: hung stud

13% chance turning into 50/50

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198858)



  ReplyFavorite

Date: October 27th, 2020 3:37 PM
Author: ,.,.,.,,...,,.....,,...

Why his job is to tell libs what they want to hear

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198871)



  ReplyFavorite

Date: October 27th, 2020 3:39 PM
Author: absolutely devastating for board libs

Cr but it will lose its palliative effect if he’s always wrong. Some other fag who’s been right in the past and wants to tell them what they want to hear will fill the void.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198881)



  ReplyFavorite

Date: October 27th, 2020 3:40 PM
Author: gibberish

Let's see where his prediction slides on election Eve.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198893)



  ReplyFavorite

Date: October 27th, 2020 3:40 PM
Author: self care



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41198897)



  ReplyFavorite

Date: October 27th, 2020 4:07 PM
Author: spritezero

what's his clique?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199153)



  ReplyFavorite

Date: October 27th, 2020 4:11 PM
Author: A Jurisprudence is Performed

it's bad. real bad.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199173)



  ReplyFavorite

Date: October 27th, 2020 5:17 PM
Author: computer fan



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199727)



  ReplyFavorite

Date: October 27th, 2020 4:10 PM
Author: Hunter S Biden (gunneratttt)

xoxo is so stunningly bad when it comes to statistics, it's sad.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199165)



  ReplyFavorite

Date: October 27th, 2020 4:21 PM
Author: ;..;.;;;.;;.;.;.;;;.;;;.;.;;;....;.


Look out guys, we have a STATISTICIAN here!

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199255)



  ReplyFavorite

Date: October 27th, 2020 5:14 PM
Author: oneforthethumb

math major and former stats teacher here

care to elaborate?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199698)



  ReplyFavorite

Date: October 27th, 2020 4:11 PM
Author: '"'""'"'''""



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199170)



  ReplyFavorite

Date: October 27th, 2020 4:23 PM
Author: commacommadotdotcomma

just do punditry and say everything is a 50/50 chance, bro

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199270)



  ReplyFavorite

Date: October 27th, 2020 5:13 PM
Author: oneforthethumb

Nate Silver is a fucking FRAUD.

Barnes is on it. Silver knows about many of the frauds committed by the mainstream media and univ polling outfits.

He needs to be sued.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199693)



  ReplyFavorite

Date: October 27th, 2020 5:15 PM
Author: .,.,;,.,..,.,.,:,,:,...,:::,...,:,.,.:...:.,:.::,.


nah dude its all good check out this infographic no way something so condescending could be wrong. i for one am glad he visualized what 12% means or i wouldve been lost

https://pbs.twimg.com/media/ElVyS25WoAA6G2Z?format=jpg&name=small

https://www.gstatic.com/tv/thumb/persons/685771/685771_v9_aa.jpg

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199705)



  ReplyFavorite

Date: October 27th, 2020 5:20 PM
Author: propagandist

cr

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199751)



  ReplyFavorite

Date: October 27th, 2020 5:31 PM
Author: borders

It's true that you can do this, but it's still incredibly sketchy b/c it's still very dishonest the way he presents it

The validation he provides on his "predictions" aren't actually predictions at all - if you look at what he puts out - it will be like "out of events our model predicted would come true with at least 0.8 probability, 87% of the time these events actually did come true"

This is very deceptive presenting this as validation - another way to translate what I just said was "out of events that were overwhelmingly obvious they would come true, 87% of the time they actually came true"

He's only validating a high threshold of precision which actually excludes a huge set of events in that field

What it doesn't tell you is "out of all events that actually came true, what % of these events did our model *predict* would come true"?

The reason he doesn't give this is why Taleb / anyone w/ statistical training and balls enough to speak out publicly against him (small set of ppl in the world) have criticized him relentlessly - b/c all he's doing is what i said originally , he's not actually willing to make *predictions* by giving a decision boundary on the model in the form of a threshold for the probability , implicitly 0.5 but by no means does it have to be 0.5, by which to say above this threshold the event is predicted yes/true, below is predicted no/false - doing this would allow actual validation as to the quality of his models, and it's not surprising the article we saw the other day showing using his model loses 6% over going w/ long-odds in soccer matches using his soccer predictions - ie one of the areas he CAN be validated in is his soccer model b/c it outputs expected goals, and it gives you a return of -6% against long-odds from that site that wrote the article

What he's doing when he puts out "validation" is he's cranking up the threshold to 0.9, restricting the validation set to only events that are easy to predict instead of all events, and saying "every time our model predicted the Dodgers would beat the Pirates, the dodgers won 94% of those games"

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199869)



  ReplyFavorite

Date: October 27th, 2020 5:37 PM
Author: oneforthethumb

thank you 🙏

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199938)



  ReplyFavorite

Date: October 27th, 2020 5:47 PM
Author: absolutely devastating for board libs

Real q: what is the point of him hiding that ball this way? Everyone just takes his 12/100 88/100as a statement of probability - even if he could argue it’s not nobody cares.

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200024)



  ReplyFavorite

Date: October 27th, 2020 5:54 PM
Author: .,.,.,.,.,...,.,,.,,.....,.,..,.,,...,.,.,,...,.


he's a charlatan

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200078)



  ReplyFavorite

Date: October 27th, 2020 6:25 PM
Author: borders

Don't get me wrong, it's not completely obvious how we *should* interpret a probability for a one time event like this - which is why decades ago in the ASA meetings statisticians were broken into quasi-religious bayesian vs classical (Fisher) stats, and would argue until near fist fights broke out - these were *philosophical* arguments about the way the world worked

So there's no one correct answer i can give you

But it's not so much that you shouldn't take his 12/100 as a probability , it's how you interpret what a probability means is the philosophical question

Classical statistics would say a probability is the limit of an infinite sum of bernoulli trials whether an event occurs or not, ie a probability represents sampling variation - the number of times an event would occur if we repeated the experimental conditions enough times

A bayesian would say that there's just the event, and a probability represents our *degree of belief* in the event occurring

These days, there's not a neat philosophical distinction between these two as different ideologies , rather they're just thought of as different tools for a job

Taleb's point is that probabilities for such an event like this should only be interpreted as odds, ie degrees of belief you're willing to actually bet against - which has the degree of psychology of betting b/c once you have "skin in the game" it lessens your motivated reasoning so that you're more likely to seek out the truth when you bear the costs of being wrong

I think the issue with Silver particularly isn't so much how we interpret his probabilities , it's that

a) that probability is only as good as the underlying mechanics giving rise to those simulations , which is more to Taleb's point

b) by refusing to place a decision boundary on his model, eg saying "above 0.6 means I predict yes, below 0.6 means i predict no" , we can't ever validate the quality of his model properly, and he only releases validation against highly likely events

His hiding the ball is perfectly natural for anyone in his position , you'll see the same thing done by others it's very common, just not from eg Gelman / Taleb for example

By not giving us a decision boundary, of course we'll naturally assume >0.5 means predict yes, but that is not necessarily the case at all in many domains - for example in credit card application fraud the tradeoff between false positives and false negatives will be much different, and so you'll tune your boundary threshold accordingly since being wrong in the direction of letting a fraudulent application get through is much more expensive than accidentally rejecting a legit application

But the heart of the issue IMO is Taleb's comments, what i listed in a) and b), and

https://statmodeling.stat.columbia.edu/2020/10/24/reverse-engineering-the-problematic-tail-behavior-of-the-fivethirtyeight-presidential-election-forecast/

might end up being some really damning evidence of misdeeds if trump wins.....

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200272)



  ReplyFavorite

Date: October 27th, 2020 5:39 PM
Author: gibberish

How was he supposed to predict putin would hack the election in 2016 or Trump would hack the post office in 2020?

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41199950)



  ReplyFavorite

Date: October 27th, 2020 6:26 PM
Author: cornbread

Cr. He's probably nervous about the election results too

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200275)



  ReplyFavorite

Date: October 27th, 2020 6:27 PM
Author: reckless monkey in a tropical forest



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200278)



  ReplyFavorite

Date: October 27th, 2020 6:27 PM
Author: '"'""'"''"



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200282)



  ReplyFavorite

Date: October 27th, 2020 6:46 PM
Author: absolutely devastating for board libs



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200377)



  ReplyFavorite

Date: October 27th, 2020 6:56 PM
Author: propagandist



(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41200437)



  ReplyFavorite

Date: October 27th, 2020 10:05 PM
Author: .....................:......:::.......;...........


I’ve been a Long time listener to his podcast. He’s been tripping over himself lately to clarify that his hallowed model doesn’t include the “effects of cheating”. We all know where that’s going to lead if trump wins

(http://www.autoadmit.com/thread.php?thread_id=4663464&forum_id=2#41201798)

No comments:

Post a Comment