Wednesday, January 09, 2013

What A Good Fit!

This is pretty remarkable regression. The scatter probably results from a sort of hysteresis - maybe the results of the previous presidential election. A three-factor regression might be even better:
Larry Bartels reminds us today that despite all the hue and cry about how Obama won despite a lousy economy, he actually did about as well as you'd expect a one-term incumbent to do with the economy he had:
[B]ased on just two factors: the income growth rate in the second and third quarters of the election year and the incumbent party’s tenure in office.

.... The 2012 election outcome [] fits the historical pattern of post-war presidential election results splendidly; Obama’s popular vote margin was 3.8%, while his expected margin (based on the preliminary tabulations of real disposable income currently available from the Bureau of Economic Analysis) was 4.6%.
Bartels' regression line is based on a simple formula that takes into account two things: number of years in office and the growth of real disposable income per capita between Q1 and Q3 of the election year. Income growth this year between Q1 and Q3 was about 0.3 percent, and when you plug that into his formula you get a prediction that Obama would win the election by 4.6 percentage points. Read his whole post for all the usual caveats and warnings.

In comments, Bartels notes that one implication of this formula is that "events before the start of the election year have no effect, for better or worse." This isn't quite true, of course.

No comments:

Post a Comment