Sam Wang's gift for understatement: "I am developing doubts about their analytical neutrality."

[Texas Lawyer]

As always, we got great election analysis from Sam Wang (at Princeton Election Consortium: http://election.princeton.edu/2012/11/12/the-final-unskewing/#more-8904).

His big three takeaway points:

* President Obama led national opinion on every single day of the final two months of the campaign.

* During this period, the only event to meaningfully move national opinion was Debate #1, which led Mitt Romney to close two-thirds of a 6-point gap between him and President Obama – overnight. Some of this gain was reversed in the closing two weeks of the campaign.

* Sandy’s measurable effect on opinion was no more than 1.0%, and even this might have reversed by Election Day.

Flexing his considerable muscles of understatement, Wang crushes Colorado researchers Bickers and Berry, who erroneously thought that Romney would get 330 electoral votes, and who now erroneously offer "a persistent false idea ... culminating in something about Hurricane Sandy":

Bickers and Berry’s claim that “the president clearly benefited from the ‘October surprise’ of Superstorm Sandy” is unsupported by data. I am developing doubts about their analytical neutrality. A second piece of evidence is that most econometric models pointed in the opposite direction to theirs. A prominent example is the prior that informed Drew Linzer’s analysis at Votamatic.com.

Thanks to Sam (as well as Nate and Drew) for consistently offering a fact based alternative the the MSM's "gut feeling" that this presidential election was a "dead heat" right up until the end.

[Mayberry Machiavelli]

1. A persistent falsehood on the right is that the Colorado model successfully predicted past elections

As far as I'm aware, this was the FIRST election the model was used to try and predict anything. The model was generated from data from past elections, and made so that it would "predict" those results if it was presented that data again, but that is retrospectively and a far cry from saying that it actually predicted those elections. It did not.

Colorado model is 0/1, batting 0%.

[Texas Lawyer]

2. The "Colorado model" was never based on anything more than wishful thinking (basing everything on

state-level economic data was a model built to give a result they chose before they built the model).