http://synapse.princeton.edu/~sam/pollcalc.htmlLikelihood analysis of all possible outcomes of election based on state-by-state polls
Calculations by Prof. Sam Wang, Princeton University. Your comments, including reports of possible errors, are welcome.
I originally did this calculation to help think about how to allocate my campaign contributions. I believe that one can make the biggest difference by donating at the margin, where probabilities for success are 20-80%. To read a discussion click here. Since trends are now strongly in Kerry's favor, I recommend that Democrats give to the Senate campaigns of Tony Knowles (D-AK) and Inez Tenenbaum (D-SC) and to the DSCC. For those of you still nervous about the national election (see the bias analysis below), I recommend the voter registration and turnout organization America Coming Together. For the optimists there is the DCCC.
This calculation is a snapshot in time. It takes a large number of state polls and calculates the likeliest number of electoral votes if the election were held today and reflected those polls.
Results as of Sunday, July 18, 2004 based on state polls:
Counting the last six polls the current probability of a Kerry win is 98 percent. Counting only the last three polls the probability is 99.98 percent.
270 electoral votes (EV) are needed to win. The current 50th percentile outcome for Kerry is 296 EV. The 95 percent confidence band is 270-322 EV.
This calculation would be affected by an overall poll bias. This could happen if sentiments have changed since the time of the polls or if a discrepancy exists between state polling methods and actual voting patterns. For the last three polls the effects of bias favoring Bush are as follows. 2 points: Kerry win 95%, 50th percentile 287 EVs (95% confidence 264-302). 4 points: 26%, 279 EVs (222-297). Note the strong threshold phenomenon between 2 and 4 points.
Current probabilities by state (rounded to the nearest percentage point): AR 15, AZ 0, FL 98, IA 100, ME 98, MI 100, MN 100, MO 11, NV 25, NH 96, NM 100, OH 26, OR 100, PA 89, WA 100, WV 18, WI 88. The calculation is currently dominated by the large states FL (98%), PA (89%), and OH (26%). In most high-likelihood scenarios, two of these are needed to get over 270 EV (my earlier posting left out PA).
Added comment: the current snapshot suggests that the threshold state is PA, where Kerry leads in 11 of the last 12 reputable polls since May 1. There is a rank ordering effect, in the sense that states tend to move together. The rank order (using the mean margin divided by the SEM) among big swing states is currently
D <-- MN - MI - FL - PA - WI - OH - MO --> R