The case for calm
November 3, 2016 Leave a comment
Okay, writing this for my wife, who asked me today, “so, should I just listen to Sam Wang instead of Nate Silver?” There’s a decent case for yes. Wang has been just as accurate in the past, he’s just way less famous. I really like that Silver is taking a fundamentally conservative approach that allows for substantial systematic polling error, but it is certainly possible he is overstating the risk.
Drum makes the case for Wang and calmness and does it using my favorite statistical concept, regression to the mean (though, Drum says “reversion” to the mean):
Reversion to the mean
This theory about response rates might explain another phenomenon that’s been much in evidence this year: reversion to the mean. You can see it pretty clearly in Sam Wang’s meta-margin:
Up through July, Hillary Clinton was ahead of Trump by a steady 3.5 points. Then she got a big spike after the Democratic convention, but it quickly reverted to around 3.5. Then she dropped a bunch after some email news and her fainting spell on 9/11—but again, the trendline quickly reverted to 3.5. Then she spiked again after the second debate and the Access Hollywood video, but reverted to 3.5 yet again.
Clinton could easily lose another point before Election Day, or she could revert back to 3.5 and stay there. I’d bet on reversion to the mean. This election features two candidates who have been around a long time and are both very well known. Almost everybody made up their minds pretty early, and nothing much has changed for the past 12 months. Hillary Clinton will most likely win by 3-4 percentage points, plus maybe a little extra because she has a way better ground game.
Ultimately, as incredibly anxious and worried as I actually am right now, the cool, rational part of me truly believes that Drum’s final paragraph is pretty spot on. I really do think Clinton will win by 3-4 nationally, with around 320 electoral votes.
Also, I’ve been meaning and meaning to write about response rates, but haven’t. Read the original YouGov piece on it or Drum’s summary in this same post. (Short version: quite probable that voters really aren’t changing their minds all that much, but rather we are seeing sizable shifts in propensity to actually answer polls from among supporters of the opposing candidates).