Nate Silver destroys Rasmussen: Rasmussen Polls biased and inaccurate-Quinnipiac and SUSA the best

[Politics_Guy25]

Rasmussen is about to go the way of Zogby. Significant errors intending to set the narrative in all states.

Here's a link:

http://www.fivethirtyeight.com

Out of the 105 polls released in Senate and gubernatorial races by Rasmussen Reports and its subsidiary, Pulse Opinion Research, missed the final margin between the candidates by 5.8 points, a considerably higher figure than that achieved by most other pollsters. Some 13 of its polls missed by 10 or more points, including one in the Hawaii Senate race that missed the final margin between the candidates by 40 points, the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998.

Moreover, Rasmussen’s polls were quite biased, overestimating the standing of the Republican candidate by almost 4 points on average. In just 12 cases, Rasmussen’s polls overestimated the margin for the Democrat by 3 or more points. But it did so for the Republican candidate in 55 cases — that is, in more than half of the polls that it issued.

If one focused solely on the final poll issued by Rasmussen Reports or Pulse Opinion Research in each state — rather than including all polls within the three-week interval — it would not have made much difference. Their average error would be 5.7 points rather than 5.8, and their average bias 3.8 points rather than 3.9.

Wow!!

[LawnKorn]

1. K&R

[FBaggins]

2. Oh yeah? So it's ok to like Nate Silver again?

As for the news that rasmussen leans right? "Duh".

K&R

[Teaser]

3. who does't like Nate Silver?

I've talked to him. Nice guy.

However, I had doubts about his methodology until this election.
He now has almost enough of a sample size to convince me.
One more election cycle will be enough for me.

[FBaggins]

4. Those who are willing to shoot the messenger...

...when the message is not to their liking.

Those who thought that by going to work for the NYT, he had joined a MSM conspiracy to influence the election.

With hundreds upon humdreds of predictions, he was about as close as it's possible to get.

[Teaser]

6. he hasn't really made hundreds of predictions

in the statistical sense. All his predictions are highly correlated, because he uses the generic national ballot numbers to seed his model, and because this was a "wave" election. So you can't regard the predictions as statistically independent. Figuring out his N from these predictions is really difficult, and quite beyond me right now.

Each election, though, is definately uncorrelated, which is why I'm weighting my trust in him based on aggregate per-election performance.

But in any even, I haven't seen people arguing that he is some kind of conspiracist for joining the NYT. But this is the internets, and that kind of thinking is rampant, so I wouldn't be surprised.

[Jennicut]

5. Really? Quinnipiac? I will really have to start trusting them then. They poll out of Hamden,

really close to where I grew up in Connecticut. They were pretty good with the Blumenthal/McMahon race and had Foley a bit ahead of Malloy though within the margin of error. I eagerly await their next poll on Lieberman. Now that is a poll I really want to see, with possible challengers in it as well.

[wisteria]

7. Rasmussen was always thought to be biased towards Republicans,

but it is good to see the numbers bare this out. They should be discredited big time before the next elections, or they will be out trying to sway the electorate once again.