Wednesday, November 5, 2008

Predicting the future

ARG's Dick Bennett, talking about Nate Silver of 538.com in the New York Times.
He hasn’t been able to predict the future.
He hasn't? Here's yesterday's Final pre-election projection from 538.




Our model projects that Obama will win all states won by John Kerry in 2004, in addition to Iowa, New Mexico, Colorado, Ohio, Virginia, Nevada, Florida and North Carolina, while narrowly losing Missouri and Indiana. These states total 353 electoral votes. Our official projection, which looks at these outcomes probabilistically -- for instance, assigns North Carolina's 15 electoral votes to Obama 59 percent of the time -- comes up with an incrementally more conservative projection of 348.6 electoral votes.

We also project Obama to win the popular vote by 6.1 points; his lead is slightly larger than that in the polls now, but our model accounts for the fact that candidates with large leads in the polls typically underperform their numbers by a small margin on Election Day.

And here are the actual votes (with NC's 11 EVs still on the table)

Barack Obama 63,764,326 (52.4%) (349 EVs)
John McCain 56,324,856 (46.3%) (169 EVs)

For a popular vote difference of 6.1% and an electoral vote spread of 349-169. The only state Nate got wrong was Indiana.

That's a scarily accurate projection of the electoral and popular vote, but John McCain's win percentage is still at 1.1% and I still won't rest until it's updated to 0.0%!

1 comment:

Tim Walters said...

NC has now gone for Obama, making Sam Wang the winner of their little predict-off. But great work from both!