View Single Post
Old 11-02-2016, 08:16 AM   #5052
ernie
Franchise Player
 
Join Date: Oct 2004
Exp:
Default

Quote:
Originally Posted by GGG View Post
I like 538 but the credit they get for the last two elections is a little overblown.

There might be 5 or 6 swing states out there so over two elections you might have 12 difficult choices. So assuming a 50/50 odds random chance gives you a 3/1000 chance of winning. Now even the 6 closest states probably have a 60% favourite which increases the chances of randomly going 11/12 or better is about 1/50.

So if in 2008 there were 50 websites predicting election results you'd expect in 2016 to have a few Nate Silvers existing. The other thing is that you'd expect eventually an election to occur where 538 would go 0/6 on swing states otherwise the probiotics assigned to the favourites wouldn't be high enough. In the end if you did the analysis I don't think you could say you have statisticly significant evidence that Nate is better than you would expect from random chance.

To me the value in any of these aggregates is doing all the leg work to interpret all of the polling out there in a constant methodology to provide a baseline of information around the spin. Also there work on inferring the effect of each state based on the behaviours of surrounding states, demographics and national trends.
It isn't just the presidential election though that he called. In 2012 he called many many more down ballot races as well. They talked about it on the Daily Show at the time.

Also to call 9 swing states correctly, something that no pollster nor any other aggregate statistician did, is not something that can just be written off.

In 2008 he called 49 of 50 states (50 of 51 if you include DC) for the presidential race. He called every single Senate race correctly.

In 2010 he called 36 of 37 gubernatorial races. 34 of 37 senate races

IN 2012 he called all 51 of 51 for the presidential election. No pollster or other aggregate models predicted every single swing state but 538/Nate did.

That is very unlikely to be random chance. He has proven to have a better model than anyone else at this point. Doesn't mean he is always correct or that his current model tweakings will be the best now but his track record does indeed speak for itself.

Last edited by ernie; 11-02-2016 at 08:27 AM.
ernie is offline