Political Math
The basic technique here is multiple regression analysis. I took a look at a whole number of independent variables, and tried to gauge their effect on one dependent variable: Obama’s two-way vote share. By “two-way vote share”, I mean the proportion Obama got of the (Obama Hillary) votes; essentially we’re throwing the Edwards, Richardson, Biden, etc. votes out. So in New Hampshire, Obama’s two-way vote share is 48.3%, and Hillary’s is 51.7% — much higher than their multi-way vote share.
I looked at pretty much every variable I could think of that we can quantify about a state and that might affect the Obama-Clinton vote share. It turns out that there are 8 or 10 that proved to be statistically significant enough for me to include them in my model.
This is a detailed statistical analysis of the votes so far in the Democratic primaries and caucuses. It is a bit more elaborate than what you get from the mainstream media. It also includes predictions, most of which look good for Obama.
