In order to ensure that this thread continues to meet TL standards and follows the proper guidelines, we will be enforcing the rules in the OP more strictly. Be sure to give them a re-read to refresh your memory! The vast majority of you are contributing in a healthy way, keep it up!
NOTE: When providing a source, explain why you feel it is relevant and what purpose it adds to the discussion if it's not obvious. Also take note that unsubstantiated tweets/posts meant only to rekindle old arguments can result in a mod action.
On February 02 2016 05:51 oneofthem wrote: nate silver isn't doing some crazy model it is just polls and stuff like endorsements. wouldn't really call it a model at all. he just had a platform.
i was telling you guys the polling numbers are a joke for a long time but you gotta go to silver to learn this apparently
I think it is fair to note that Nate Silver was distinguished in his analysis of 2008 and 2012.
i'd say those were popularizing as well. if you aggregate polls and look at historical trends you can get to about the same conclusions. the princeton group did pretty well doing the same method.
not to diss silver it's just that primary stage polling is so noisy and both the election and candidate impressions are far from settled.
On February 02 2016 05:51 Plansix wrote: The best pollsters are the ones who tell you when they don’t have enough information. Anyone can make a guess based on the information presented to them.
His book talks about this quite a bit. When he makes a prediction, it's based off of the information he has at the time. A bad forecaster is one who doesn't acknowledge this and doesn't change his forecast when new/more information comes up. It's a really good read and I'd definitely suggest it.
Granted, this election season has been a clusterfuck, so I've taken his predictions with twitch levels of salt.
On February 02 2016 05:27 TheTenthDoc wrote: I hope Rand Paul and O'Malley win the caucuses.
Where are your poll gods now???
E Plebius Unum
In Nate Silver we trust
I mean they have an explanation already for why being wildly wrong wouldn't be their fault, but I'm predicting this will be the most wrong Nate and crew have been about an election.
It was a joke, in case you missed it.
538 says they basically have no idea what's going to happen
Reposting poll b/c 2 pages already passed:
On February 02 2016 03:10 ticklishmusic wrote: Alright, let's poll it up:
On February 02 2016 05:51 oneofthem wrote: nate silver isn't doing some crazy model it is just polls and stuff like endorsements. wouldn't really call it a model at all. he just had a platform.
i was telling you guys the polling numbers are a joke for a long time but you gotta go to silver to learn this apparently
I think it is fair to note that Nate Silver was distinguished in his analysis of 2008 and 2012.
i'd say those were popularizing as well. if you aggregate polls and look at historical trends you can get to about the same conclusions. the princeton group did pretty well doing the same method.
not to diss silver it's just that primary stage polling is so noisy and both the election and candidate impressions are far from settled.
Of course everyone says that in hindsight. At the time when he predicted the election for Obama both times people called him a liberal shill and questioned his ability to read polls. He took a lot of heat both elections and had nearly perfect predictions for both. But now people are saying what he does isn’t impressive, even though he is one of the few people doing it.
And people also over simply what he does to taking an aggregate of polls. He assesses the accuracy of polls based on historical data and previous accuracy/trends. He also reviews the polling agency’s methodology for best practices, which very few people or news agencies do. He is one of the only people talking about the quality of information, rather than just assuming it is all correct.
the man went 50/50 (EDIT: as Seuss clarified, he got every state right) on predicting which states went for obama and romney. that's a very impressive bit of prediction.
i wonder if nate silver would go to a betting site and dump like 100 grand on his best predictions to make mad bank, if i were him i would
On February 02 2016 06:25 ticklishmusic wrote: the man went 50/50 on predicting which states went for obama and romney. that's a very impressive bit of prediction.
To be clear, 50/50 in this case means 50 out of 50 rather than 50%. Though he missed one delegate in some state because of weird arcane rules or somesuch.
That Sam Wang guy sounds salty AF he didn't get super popular for his predictions.
I mean Neil Degrasse Tyson is super popular and he's a great astrophysicist but he's not John C Mather (won the nobel forresearch into cosmic background radiation). He just made science cool and is kinda nerd famous.
And I am not at all shocked that statisticians have opinions about his work. That doesn’t make his work any less valid or impressive because someone else is doing it as well.
ticklishmusic: I got that impression as well. Though he leaves out the part where Nate Silver is a public facing person and catches tons of heat and criticism because of that.
Yes. But that article reads like the most sour of grapes. Like rather than celebrating a guy using their craft to prove everyone else wrong, he spends most of the article talking about how basic Nate Silver’s work is. He is the one movie reviewer who feels the need to publish his not glowing review of “Popular movie X” 2-3 weeks after it came out, explaining in detail why everyone else was caught up in the hype machine. But not him.
On February 02 2016 07:07 Plansix wrote: And I am not at all shocked that statisticians have opinions about his work. That doesn’t make his work any less valid or impressive because someone else is doing it as well.
ticklishmusic: I got that impression as well. Though he leaves out the part where Nate Silver is a public facing person and catches tons of heat and criticism because of that.
Trump wins all 50 states (for the nomination) 99.9% confidence, Nate's got nothing on me ;P
Both articles are super salty. I mean look at this opening from the second one.
Obama may have won the presidency on election night, but pundit Nate Silver won the internet by correctly predicting presidential race outcomes in every state plus the District of Columbia — a perfect 51/51 score.
Now the interwebs are abuzz with Nate Silver praise. Gawker proclaims him “America’s Chief Wizard.” Gizmodo humorously offers 25 Nate Silver Facts (sample: “Nate Silver’s computer has no “backspace” button; Nate Silver doesn’t make mistakes”). IsNateSilverAWitch.com concludes: “Probably.”
This thing nerd oozes envy of the cool kid that isn't as smart.
Really Silver was praised for a lot of reasons, including a ton of public ridicule from his peers for his predictions and being an interesting writer that breaks this stuff down for the public. Nate Silver isn’t the most impressive math wizard on the planet. Just like Neil Degrasse Tyson is not the most impressive astrophysicist on the planet. But both fill a role in the public that neither of those authors can fill due to skills they do not process, have not honed or simply under value.
Shit, I just saw people reporting that he said that, but I didn’t think it was on camera. That is very close to “attempting to insight violence,” use of speech. Not that I am really shocked at all.
EPT
