What do you get if you use the turnouts for WI or 2010?
I'm taking Rasmussen's polling results and converting them into probabilities of winning.
My model assumes that the Rasmussen poll is an accurate reflection of the percentage split of votes on election day, within a plus or minus margin of error. I simulate the margin of error in the poll result.
As far as turnout affects the polling result, I let Rasmussen do that heavy lifting when he determines his poll population and publishes his findings.
-PJ