# Did the demographic forecast model really beat the polls?

“Based on the African-American share of the electorate in 2008, the Democratic share of the electorate in 2008, and the fact that all three states are located outside of the South, the model predicts Sanders victories in Indiana and Oregon, a Clinton victory in Kentucky, and a tie in West Virginia. The main reason why Sanders is favored in Indiana and Oregon while Clinton is favored in Kentucky is that the Democratic share of primary voters in Kentucky was much higher than in Indiana or Oregon in 2008. While Oregon’s primary, like Kentucky’s, is technically closed, self-identified independents made up a much larger share of Oregon’s Democratic primary voters in 2008, and I assume that this will also be the case in 2016. And while West Virginia holds an open primary, Democrats made up almost 80% of the voters in 2008.”
http://www.centerforpolitics.org/crystalball/articles/forecast-model-beats-the-polls/

Abramowitz’s model:
Y = 5.1 + 11.0 X(1) + 0.2 X(2) + 0.6 X(3)

X(1): South
X(2): AfricanAmerican
X(3): Democrats

Y: Clinton’s vote share

It reflects the number or non-existence of the “self-identified independents”.

Y = 5.1 + 11.0 X(1) + 0.2 X(2) + 0.6 X(3)

If you replace Y with 100 - Z ,
Z = 94.9 - 11.0 X(1) - 0.2 X(2) - 0.6 X(3).

Is this right? (Z refers to Sanders’ vote share.)

What do you think about the difference between two equations?
Why are the two constants so different?
5.1 and 94.5

Am I right in thinking that Y + Z = 100 ?

"[T]he model predicts Sanders victories in Indiana and Oregon, a Clinton victory in Kentucky, and a tie in West Virginia. "

I think that what Bernie Sanders calls “momentum” is hidden in the constant of the forecast model.
Paul Krugman contends that there is no such thing as momentum. But, It could be found when you compare data at several points. A set of “cross-sectional” data at a point can neither prove nor disprove the existence of momentum.