31 March 2014

A forecasting model that does not utilize a Sensitivity Analysis of alternative forecast assumptions is incomplete. This analysis of 10 battleground states is based on various voter turnout and vote share scenarios.


The states are: CO FL IA NC NH NV OH PA VA WI


In 2008, Obama won the recorded vote by 52.9%-45.6%.
He won the unadjusted state exit poll weighted aggregate by 58-40.5%
The True Vote Model indicated that he won by 58.0-40.3%



In the 10 states, Obama’s…

Average 2008 recorded share: 53.3%

Average 2008 exit poll: 57.8%



2012 True Vote Model: 54.9%

2012 Poll-based projected share: 51.6%



The following assumptions apply to all 10 states:

1. The number of returning voters is based on the 2008 state exit poll.

2. There is 5% voter mortality (1.25%/year)

3. Turnout: 95% of Obama 2008 voters; 97% of McCain voters.

4. Obama wins 92% of returning Obama voters and 5% of McCain.

5. Romney wins 95% of returning McCain voters and 8% of Obama.



Given the above, there are two sets of sensitivity tables.

Table 1: Obama shares of returning Obama voters (87-97%); McCain voters (0-10%)



Table 2: 2008 turnout of Obama voters (92-98%); McCain voters (94-100%)



There are 9 scenario combinations in each table.


Of the total 18 scenarios, Obama won 14 in FL, 17 in OH, 15 in NC, 12 in CO, 17 in NV. He won all 18 scenarios in WI, VA, PA, IA and NH.



Link to the Sensitivity Analysis.



The analysis indicates that Obama should do quite well in these battleground states – unless, of course, the elections are stolen.