Antagonism isn't perpetual

Antagonism isn't perpetual



If you recently glanced at the polls and the election markets, then you would be forgiven to believe that a landslide election is looming.  It's likely not (the opinion of even Nate Silver's 538), and the spreads have the potential to revert in surprising ways between now and Election Day.  The drumbeat of negative news against Donald Trump may not cause further damage.  We've discussed numerously, starting on October 11 and October 12, that Hillary Clinton's runaway spread would revert (here, here, here, here).  Of course that's a stand taken against a popular headwind, but also an opportunity to make money on an election bet that is mispriced.  For example, when we wrote the reversion article, the betfair ask that Mr. Trump's popular vote could remain in the 40's% was only priced at 1:6 odds.  The 538 site also reflected this, as shown below (and still ascending through October 16 to now a >40% reversion!) But we -and other academic statisticians- knew that this was faux election probability, and advised hundreds of thousands to remain vigilant against planned mainstream misinformation.  Incidentally, today's betfair bid is 20% higher; not many investments have risen 20% in just the past couple days.  And the wager could explode to600% profit, exposing how steeply deluded the polls have been.  This article isn't merely about gambling, but goes to the heart of what makes polls different among one another, and across time.  And what should we be cautious of when interpreting the information, while almost never reading (and sometimes not having access to) all the underlying probability details of the poll generation?  In particular, we'll delve into the inconspicuous L.A. Times poll here, where for much of the past month they showed Donald leading Hillary.  How did they come to that, and what value is there in paying attention to alleged outliers?  



Cont....