@fivethirtyeight Steal underpants?
— John Markos O’Neill (@johnmarkos) October 27, 2012
In a review of Nate Silver’s The Signal and the Noise, Samuel Popkin surveys the recent history of polling analysis and notes how Nate’s work improved upon the averaging approach pioneered by RealClearPolitics.com in 2000:
Silver has taken the next major step: constantly incorporating both state polls and national polls into Bayesian models that also incorporate economic data…. [Bayesian models] force us to ask how probable we believe something to be—say an Obama victory—before collecting new evidence and revising our level of uncertainty. Silver explains why we will be misled if we only consider significance tests—i.e., statements that the margin of error for the results is, for example, plus or minus four points, meaning there is one chance in twenty that the percentages reported are off by more than four.
Calculations like these assume the only source of error is sampling error—the irreducible error—while ignoring errors attributable to house effects, like the proportion of cell phone users, one of the complex set of assumptions every pollster must make about who will actually vote. In other words, such an approach ignores context in order to avoid having to justify and defend judgments.
Previous Dish on Silver’s book here and here. Above South Park reference here, in response to a recent Malkin Award.
The Dish 