Tweet |

- The graph above includes events that may have influenced the candidates' probability of winning. We have tried to find events that were turning points in the election campaigns. If there are other events that you think caused some of the turning points in the election, please let us know via the contact page.
- We can see from the graph that Santorum's announcement of pulling out of the race on April 10 had a small effect, and we see a decrease in Romney's probability of winning from around 10% to around 5% a month later.
- On May 9th, Obama came out in support of gay marriage, and this seems to be correlated with a strong decline in his chance of winning, going from 95% on May 9th to 82% on June 16.
- The next two events, Obama's executive order on immigration on June 15th, and the Supreme Court's upholding of the Affordable Care Act ("Obamacare") on June 28th, did not seem to have much of an effect until around July 14, when things started going south for Obama.
- It's not yet clear what caused the downturn that began on July 14, but it could be the delayed reaction to the previous two events, since polls don't immediately reflect events on the national stage.

- Romney picking Ryan as his running mate on August 11 had a modest effect on Romney's chances, which increased from 19% on August 11 to about 27% on August 19. However, the effect seems to have been short-lived, as Romney's chances fell to around 23% just before the Republican National Convention (RNC).
- The RNC itself seems to have had a decent effect on Romney's chances, which went from around 23% before the RNC to around 30% a week after the RNC began.
- However, the DNC seems to have had a huge effect on Obama's chances, which went from around 70% before the DNC started to around 86% ten days after the DNC began.
- The leaked Romney "47%" video initially had a considerable effect on the polls, pushing Obama from 80% on Sep 17 to 90% on Sep 22, but the effect was short-lived. By Sep 26, the probabilities had gone down to pre-"47% video" levels.
- The latest event that has had a strong effect on the results is the first presidential debate, in which Obama greatly underperformed, according to just about everyone. That changed Obama's probability of winning from 83% on Oct 3, to 67% on Oct 7. It seems to have been mostly a short-lived effect since, by Oct 12 Obama was back up to 79%.

In adition to an estimate of the probability of winning the election, it's also instructive to see how sensitive this probability is to changes in state poll results. That is, which states impact the result the most if their polls change in favor of one candidate or another?

In the figure on the left, we see the resulting probability of an Obama win, given changes in state polls from the five states with the most potential upside for Obama or downside for Romney.

To keep the figure easy to read, it only includes the resulting probability of an Obama win. The resulting probability of a Romney win is simply 100 minus the probability of an Obama win.

As of November 6th, election day, Pennsylvania, Ohio, Michigan, Florida, and Virginia have the most potential upside for Obama. If any of their state polls change by 10% in favor of Obama (i.e. 5% switch from Romney to Obama in any state), Obama's probability of winning increases to 76%-81% and Romney's probability of winning drops to 19%-24%.

The results in this plot may not be as informative as one would hope, though. This is due to the fact that this plot shows how the resulting probability of winning changes *if* a particular state's poll results change by a certain amount. But it doesn't capture the likelihood that that state's poll will change by that amount. Therefore, keep this caveat in mind when interpreting the plot.

This figure is similar to the previous one, with the only difference being that it corresponds to changes in state polls from the five states with the most potential downside for Obama or upside for Romney.

Again, to keep the figure easy to read, it only includes the resulting probability of an Obama win. The resulting probability of a Romney win is simply 100 minus the probability of an Obama win.

As of November 6th, election day, Florida, North Carolina, Arizona, Georgia, and Missouri have the most potential downside for Obama. If Florida state polls change by 10% in favor of Romney (i.e. 5% switch from Obama to Romney), Obama's probability of winning decreases to 61% and Romney's probability of winning jumps to 39%. If any of the other four state polls change by 10% in favor of Romney (i.e. 5% switch from Obama to Romney), Obama's probability of winning decreases to 66%-67% and Romney's probability of winning jumps to 33%-34%.

In addition to looking at probabilities of Obama or Romney winning, we can also look at the probabilities of achieving different electoral vote results. That is, what is the probability that Obama or Romney will collect say, 270, 285, or 300 electoral votes? (Note that the probability of either of them winning the election is the probability that they will collect 270 or more electoral votes).

The figure on the left shows the probabilities of each of the candidates achieving given electoral vote totals, which vary from zero to 538. The points where the curves are the highest correspond to the most likely electoral votes for each candidate.

As of November 6th, election day, the most likely electoral vote outcome is 287 for Obama and 251 for Romney.

comments powered by Disqus