Outcome Prediction System

I'm going to try something tonight, that is to predict the final outcome, as returns come in, based on vote totals in some key counties.

Sound fun?

I'll provide a little background on what I'm doing in this post and than start an actual Outcome Estimator post when returns start coming in.

I will be doing this at MN Progressive Project so that I don't have to keep two separate threads going.

First off lets look at a chart of vote shares by selected county in Senate and Governor's races since 2000.

The chart below has four columns that are averages of vote shares in those situations, so where it says "DFL %, win" that's the average DFL share of the vote in that county when the DFL candidate wins. Where is says "diff" that's the difference between vote share in wins and losses.

This chart is not super exciting, so prepare yourself.



What you can see is that all of these key counties show a difference for the candidate who wins versus the candidate who loses except one, that is St. Louis County. So while in a DFL primary watching what happens in St. Louis County is key, in a general election it's less so.

This is not to say that St. Louis County should be taken for granted, just that the Democrat is going to do well there regardless of how they do in the rest of the state. The other counties listed though, can be used to provide a very accurate forecast of the final vote share.

How accurate?



Not too bad. If the race is close, then we're waiting for St. Louis County, but this will give us an indication of weather that will be the case or not once votes start coming in from the Twin Cities and surrounding suburbs.