# Nate Silver / 538 Was Right

**URL:** <https://boards.straightdope.com/t/nate-silver-538-was-right/640181>\
**Category:** Politics & Elections\
**Created:** [November 7, 2012, 5:43am UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181 "2012-11-07T05:43:57Z")\
**Posts on this page:** 20\
**Page:** 3

<div class="post-metadata">

**Author:** ![al27052](https://avatars.discourse-cdn.com/v4/letter/a/41988e/32.png) [@al27052](https://boards.straightdope.com/u/al27052)\
**Post date:** [November 7, 2012, 1:49pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/41 "2012-11-07T13:49:56Z")

</div>

> [@stpauler](#):
>
> Oddly enough the website [Natesilverwrong.com](http://www.natesilverwrong.com/) has been down all morning.

How shocking!😉

---

<div class="post-metadata">

**Author:** ![zut](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/zut/32/2875_2.png) [@zut](https://boards.straightdope.com/u/zut)\
**Post date:** [November 7, 2012, 1:50pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/42 "2012-11-07T13:50:16Z")

</div>

> [@Enginerd](#):
>
> His state predictions have uncertainties attached to them that represent (I think) the 95% confidence interval. For example, Virginia was projected to go 50.7/48.7 Dem/Pub with an error of +/- 2.5%. If we assume the 0.6% Jill Stein/Gary Johnson/Roseanne Barr/etc. remains constant, any Obama result between 48.2% and 53.2% would be considered a “hit” for Silver. He gave Obama a 79% chance of carrying the state, but Romney could have won it while Silver’s model was right, and Obama could have won even if the model were wrong.
> 
> To check his accuracy, you’d have to go state by state, comparing the actual vote shares to Silver’s predicted shares. With a 95% confidence interval, I’d expect hi to hit on something like 46-49 of the 50 states. If he hits on all of them, he’s underestimating the confidence of his model; if he his on too few, he’s overestimating it. I’d guess he’s got a pretty good handle on it, though.

For fun, I compared the 538 predictions with the current totals at CNN (which as of now are not 100% complete, so there’s some error here). I normalized the 538 predictions using the margin of error for each state, and compared all results to a normal distribution curve.

The differences fall almost exactly on the normal distribution; importantly, there doesn’t seem to be much bias in either direction. As you’d expect, two states fall outside of the 95% margin of error: Hawaii and West Virginia, but both are by small amounts.

So, pretty good job by my amateur eye.

---

<div class="post-metadata">

**Author:** ![Si\_Amigo](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/si_amigo/32/2877_2.png) [@Si\_Amigo](https://boards.straightdope.com/u/Si_Amigo)\
**Post date:** [November 7, 2012, 2:03pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/43 "2012-11-07T14:03:30Z")

</div>

> [@Zebra](#):
>
> Nate Silver is smart. He makes things go.

Do not even think of kidnapping Nate to run your own private operations; he will outsmart you if you try. 😉

---

<div class="post-metadata">

**Author:** ![regginbrow](https://avatars.discourse-cdn.com/v4/letter/r/ba9def/32.png) [@regginbrow](https://boards.straightdope.com/u/regginbrow)\
**Post date:** [November 7, 2012, 2:08pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/44 "2012-11-07T14:08:50Z")

</div>

> [@stpauler](#):
>
> Oddly enough the website [Natesilverwrong.com](http://www.natesilverwrong.com/) has been down all morning.

What used to be on the site?

---

<div class="post-metadata">

**Author:** ![Fotheringay-Phipps](https://avatars.discourse-cdn.com/v4/letter/f/d9b06d/32.png) [@Fotheringay-Phipps](https://boards.straightdope.com/u/Fotheringay-Phipps)\
**Post date:** [November 7, 2012, 2:25pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/45 "2012-11-07T14:25:33Z")

</div>

I agree with some of the posters who say that further in-depth analysis would be appropriate, but from the initial look of things, this does look like support for Nate Silver’s model.

And a big win for him personally. He achieved a lot of prominence in this election cycle, much of it due to attacks on him from conservatives, whose own predictions proved to be very wrong.

Silver is a huge winner. He is now one of the leading election/poll analysts in the country, and will no doubt be a featured commentator on all sorts of other media. (The only problem he has in this regard is that his expertise is very heavily data and analysis driven, and it’s harder for him to just show up on television shooting off his mouth at random than it is for the more conventional babblers.)

---

<div class="post-metadata">

**Author:** ![JohnGalt](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/johngalt/32/184_2.png) [@JohnGalt](https://boards.straightdope.com/u/JohnGalt)\
**Post date:** [November 7, 2012, 2:31pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/46 "2012-11-07T14:31:18Z")

</div>

As I was reading this I thought “cool!” - Nate Silver is a Straight Dope fan. Then you burst the bubble.

On the other hand, it seems like SDMB is something he’d really enjoy. Does anyone know if he follows us? It’d be interesting to hear his views about the comments made here.

> [@kaylasdad99](#):
>
> Fair dos to you, **OMG**. Just last week, I was sharing a drink with Nate in the Copacabana Room at the Polo Lounge, and he was looking really despondent. “I just don’t seem to be able to get through to this one guy over on the SDMB,” he told me. “Maybe I’m on the wrong track with this stuff after all.”
> 
> All I could do was tell him to buck up (and buy him another drink). He saw the wisdom in my advice and stuck to his model.
> 
> But you ALMOST got him to waver! Better luck next time.
> 
> Disclaimer: None of that little anecdote actually happened.

---

<div class="post-metadata">

**Author:** ![leftfield6](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/leftfield6/32/18780_2.png) [@leftfield6](https://boards.straightdope.com/u/leftfield6)\
**Post date:** [November 7, 2012, 2:47pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/47 "2012-11-07T14:47:21Z")

</div>

> [@regginbrow](#):
>
> What used to be on the site?

Fiction, apparently.

---

<div class="post-metadata">

**Author:** ![Tom\_Scud](https://avatars.discourse-cdn.com/v4/letter/t/f08c70/32.png) [@Tom\_Scud](https://boards.straightdope.com/u/Tom_Scud)\
**Post date:** [November 7, 2012, 2:54pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/48 "2012-11-07T14:54:04Z")

</div>

Sam Wang did better in the Senate races (though he picked Florida for Romney), at least if Tester holds on to his lead (as of an hour ago) in Montana.

---

<div class="post-metadata">

**Author:** ![Marley23](https://avatars.discourse-cdn.com/v4/letter/m/45deac/32.png) [@Marley23](https://boards.straightdope.com/u/Marley23)\
**Post date:** [November 7, 2012, 3:03pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/49 "2012-11-07T15:03:32Z")

</div>

One of the good things about this electoral cycle is that it sounds like we’ve now achieved SABRmetrification of poll analysis. I don’t know if the networks will get much better at reporting polls in context, but that kind of context will get more attention and it’ll be easier to find.

---

<div class="post-metadata">

**Author:** ![John\_Mace](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/john_mace/32/185_2.png) [@John\_Mace](https://boards.straightdope.com/u/John_Mace)\
**Post date:** [November 7, 2012, 3:03pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/50 "2012-11-07T15:03:39Z")

</div>

> [@Really\_Not\_All\_That\_Bright](#):
>
> Charles Krauthammer already jabbering on Fox about how Romney lost because he was too liberal.

Did God smite CK with boils on this face or something?

---

<div class="post-metadata">

**Author:** ![DigitalC](https://avatars.discourse-cdn.com/v4/letter/d/ebca7d/32.png) [@DigitalC](https://boards.straightdope.com/u/DigitalC)\
**Post date:** [November 7, 2012, 3:15pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/51 "2012-11-07T15:15:49Z")

</div>

Could i have simply taken the last say, ten, polls on every state and come up with pretty much the same results as Silver?

---

<div class="post-metadata">

**Author:** ![Jas09](https://avatars.discourse-cdn.com/v4/letter/j/d07c76/32.png) [@Jas09](https://boards.straightdope.com/u/Jas09)\
**Post date:** [November 7, 2012, 3:33pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/52 "2012-11-07T15:33:01Z")

</div>

> [@Fotheringay-Phipps](#):
>
> Silver is a huge winner. He is now one of the leading election/poll analysts in the country, and will no doubt be a featured commentator on all sorts of other media. (The only problem he has in this regard is that his expertise is very heavily data and analysis driven, and it’s harder for him to just show up on television shooting off his mouth at random than it is for the more conventional babblers.)

And he’s just not very good at television, although not as painfully bad as he was initially.

---

<div class="post-metadata">

**Author:** ![Jas09](https://avatars.discourse-cdn.com/v4/letter/j/d07c76/32.png) [@Jas09](https://boards.straightdope.com/u/Jas09)\
**Post date:** [November 7, 2012, 3:35pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/53 "2012-11-07T15:35:10Z")

</div>

> [@DigitalC](#):
>
> Could i have simply taken the last say, ten, polls on every state and come up with pretty much the same results as Silver?

Yeah, pretty much. That’s what RCP does and their “no toss-up” map was exactly right as well (pending FL). However if Florida does go to Obama by razor-thin margins then Silver would have been marginally better there (RCP had Romney by 1.5 in their last average).

I have no doubt Nate (and others) will do some analysis over the next few weeks measuring the average errors of the various methods.

---

<div class="post-metadata">

**Author:** ![Siam\_Sam](https://avatars.discourse-cdn.com/v4/letter/s/d78d45/32.png) [@Siam\_Sam](https://boards.straightdope.com/u/Siam_Sam)\
**Post date:** [November 7, 2012, 3:36pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/54 "2012-11-07T15:36:21Z")

</div>

I dunno. He’s _still_ giving Obama only a 90.9% chance.

---

<div class="post-metadata">

**Author:** ![The\_Dord](https://avatars.discourse-cdn.com/v4/letter/t/3be4f8/32.png) [@The\_Dord](https://boards.straightdope.com/u/The_Dord)\
**Post date:** [November 7, 2012, 3:37pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/55 "2012-11-07T15:37:52Z")

</div>

> [@gamerunknown](#):
>
> Yes, Nate Silver colluded with the other pollsters in order to depress turnout and defeat the candidate sober enough to get America back on track again. Only time will tell how disastrous this presidency will be and whether patriotic Americans will allow the greatest country in the world to lapse into Populism and Communism.
> 
> The one relief is that the _bien pensants_ were incapable of suppressing true Americans from acceding to the [House and the State legislatures](http://www.redstate.com/2012/11/07/a-constitutional-republic-not-a-democracy/).

[You](http://boards.straightdope.com/sdmb/showthread.php?p=15671229#post15671229) [seem](http://boards.straightdope.com/sdmb/showthread.php?p=15671206#post15671206) [off](http://boards.straightdope.com/sdmb/showthread.php?p=15671114#post15671114) your [rocker](http://boards.straightdope.com/sdmb/showthread.php?p=15671195#post15671195).. and then [some](http://boards.straightdope.com/sdmb/showthread.php?p=15671067#post15671067).

---

<div class="post-metadata">

**Author:** ![John\_Stamos\_Left\_Ear](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/john_stamos_left_ear/32/3198_2.png) [@John\_Stamos\_Left\_Ear](https://boards.straightdope.com/u/John_Stamos_Left_Ear)\
**Post date:** [November 7, 2012, 3:38pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/56 "2012-11-07T15:38:53Z")

</div>

> [@The\_Dord](#):
>
> [You](http://boards.straightdope.com/sdmb/showthread.php?p=15671229#post15671229) [seem](http://boards.straightdope.com/sdmb/showthread.php?p=15671206#post15671206) [off](http://boards.straightdope.com/sdmb/showthread.php?p=15671114#post15671114) your [rocker](http://boards.straightdope.com/sdmb/showthread.php?p=15671195#post15671195).. and then [some](http://boards.straightdope.com/sdmb/showthread.php?p=15671067#post15671067).

I reported that poster for what I think is thread-shitting and trollish behavior. We’ll see what the Modmins think…

---

<div class="post-metadata">

**Author:** ![markdash](https://avatars.discourse-cdn.com/v4/letter/m/ba8739/32.png) [@markdash](https://boards.straightdope.com/u/markdash)\
**Post date:** [November 7, 2012, 3:41pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/57 "2012-11-07T15:41:19Z")

</div>

> [@Marley23](#):
>
> One of the good things about this electoral cycle is that it sounds like we’ve now achieved SABRmetrification of poll analysis. I don’t know if the networks will get much better at reporting polls in context, but that kind of context will get more attention and it’ll be easier to find.

And of course we’ll have to listen to a bunch of old fogies droning on about pollsters not living in their mother’s basement.

---

<div class="post-metadata">

**Author:** ![bup](https://avatars.discourse-cdn.com/v4/letter/b/6bbea6/32.png) [@bup](https://boards.straightdope.com/u/bup)\
**Post date:** [November 7, 2012, 4:05pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/58 "2012-11-07T16:05:09Z")

</div>

> [@Jas09](#):
>
> And he’s just not very good at television, although not as painfully bad as he was initially.

But even the \*way \*he’s bad at television fits right into our preconceived notion of what a wonk should be.

He’s got a socially awkward laugh and a nervous smile. He’s a pocket protector away from being a self-parody. It’s perfect.

Off-topic: [unskewedpolls.com](http://unskewedpolls.com) got it wrong. Their last post - exit polling (done on the web) had[Romney with the vote well in hand.](http://unskewedpolls.com/qstarnews_exit_poll_2012.cfm)

---

<div class="post-metadata">

**Author:** ![pulykamell](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/pulykamell/32/3166_2.png) [@pulykamell](https://boards.straightdope.com/u/pulykamell)\
**Post date:** [November 7, 2012, 4:08pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/59 "2012-11-07T16:08:32Z")

</div>

Has anyone posted [the Nate Silver parody](http://www.washingtonpost.com/blogs/election-2012/wp/2012/11/07/nate-silver-twitter-parody-has-a-psychedelic-election-night/) twitter feed. It’s awesome stuff.

A sample:

> [@](#):
>
> ## The last Aztec shaman whispered to me his methodology. “Don’t oversample partisans,” he warned. “Tenochtitlan fell to independent voters.”
> 
> I carved tonight’s projection on a sapling deep in the Rocky Mountains. He who finds it wins Colorado.

---

<div class="post-metadata">

**Author:** ![Kevbo](https://avatars.discourse-cdn.com/v4/letter/k/e47774/32.png) [@Kevbo](https://boards.straightdope.com/u/Kevbo)\
**Post date:** [November 7, 2012, 4:40pm UTC](https://boards.straightdope.com/t/nate-silver-538-was-right/640181/60 "2012-11-07T16:40:54Z")

</div>

> [@John\_Mace](#):
>
> Did God smite CK with boils on this face or something?

Political commentary is just is off season gig. [This](https://www.google.com/search?q=grinch&sugexp=chrome,mod%3D0&safe=active&um=1&ie=UTF-8&hl=en&tbm=isch&source=og&sa=N&tab=wi&ei=i46aUI-BPKXW0QGAqYFw&biw=1599&bih=809&sei=kI6aUI3fKenj0gHjtYC4Bg) is why you don’t hear much from him around the holidays.

[Previous page](https://boards.straightdope.com/t/nate-silver-538-was-right/640181.md?page=2)

[Next page](https://boards.straightdope.com/t/nate-silver-538-was-right/640181.md?page=4)
