This is probably a good time to link to my book: amazon.com/The-Signal-Noi…
— Nate Silver (@fivethirtyeight) November 7, 2012
NH goes to Obama. The election's over.
— Sam Wang (@SamWangPhD) November 7, 2012
2012 Was the Moneyball Election bit.ly/Xixg5C
— The Monkey Cage (@monkeycageblog) November 7, 2012
The stats geeks were right about the swing states. Actually, Obama did a bit better than even they expected. Small margins in the swing states, but wins again and again.
And they were right about Rasmussen's right-side sample-weighting bias.
Neuroscientist Sam Wang and the Princeton Electoral Consortium relied on the combined stat-analytic talents of university psychologists, mathematicians, political scientists and economists to forecast Obama's Electoral College victory with a high degree of confidence early on.
Philip Tetlock also wins. As Tetlock found in 20 years of research, even crude stats-based algorithms outperform pundit forecasts.
Nate Silver withstood vicious attacks from the right. Dean Chambers, the latest go-to numbers guy for the GOP wrote the following about Nate Silver:
Nate Silver is a man of very small stature, a thin and effeminate man with a soft-sounding voice that sounds almost exactly like the “Mr. New Castrati” voice used by Rush Limbaugh on his program. In fact, Silver could easily be the poster child for the New Castrati in both image and sound. Nate Silver, like most liberal and leftist celebrities and favorites, might be of average intelligence but is surely not the genius he's made out to be. His political analyses are average at best and his projections, at least this year, are extremely biased in favor of the Democrats.
If you know about Nate Silver's personal history, you'd know that he was a precocious math whiz and he earned a degree in Economics from the University of Chicago. Anyone acquainted with U of C would rule out the possibility that Silver is merely of average intelligence. And as everyone else has asked, what the hell does an analyst's stature and macho score have to do with forecasting? This comment alone tells you that the noise in Chambers' mind is drowning out the signals.
Over the weekend, Michael Barone, George Will, Dick Morris and many other conservative pundits rejected Silver's forecasts and predicted huge margins of Electoral College victory for Romney. Did these older, well-to-do, white men imagine that their personal surroundings provide better information than that obtained by the obsessed number crunchers who analyzed samples county by county?
What I haven't been able to find is solid information on how each party did with turnout relative to the range of pollster assumptions. My impression is that turnout was high across the board, but if that's true, were there party differences in the levels of exceeded pollster expectations? This is of interest because Obama's team relied heavily on the findings of recent voter-turnout field experiments. Republicans ignored this research, going instead with traditional methods, perhaps because they roll their eyes when it's suggested that academic researchers might know some things that don't arise from tradition or gut feelings.
Do you think anything that has happened will cause Silver's critics to question any of their assumptions about what they know and how they know it? Maybe some will, but it's more likely the narrative will be rewritten to preserve pre-existing partisan beliefs. For example, there is already talk of a hardcore conservative candidate being the road to victory in 2016, as if Romney lost because he wasn't a Santorum. They want to throw out the remaining Republican pragmatists and go full-on ideologue. Good luck with that revision of the script.
Comments