a percentage of voters decide to change their vote). This is the first result with using June polls. In future posts, I will add a more deeper analysis of swing scenarios. At the moment, the result is that Hilary Clinton will win the election with very high probability.
The statistical analysis has been performed by using the most recent polling data from here. The minimum sample size is around 500 people. The analysis employs an imprecise probability robust Bayesian approach in which robustness is evaluated with respect to the following swing scenarios:
- Best for Clinton: in each state the preference of c=2 people among the n polled is changed from Trump to Clinton.
- Best for Trump: in each state the preference of c=2 people among the n polled is changed from Clinton to Trump.
In practice, we are assuming that two voters in each State lied during the poll (or changed their mind) and we test how this affects the prediction of the election result. These two cases are naturally obtained by applying a Bayesian approach in which prior ignorance is modelled through a set of near-ignorance prior probabilities. Under this view, changing the preference of the 2 voters is equivalent to test the robustnees of the inferences to the choice of the prior model. The probability of winning of the two candidates is shown in the following bar-plot, where the blue-bar refers to the "Best for Clinton" case and the red-bar to the "Best for Trump" case. In the "worst for Clinton" case, the probability of winning of Clinton is 95% and, thus, the probability in favour of Trump is just 5% (the blue bars).
From the histogram, it can be noticed that at the moment there is not much uncertainty. Clinton is going to win the election with very high probability.
This is the electoral map for the 95% case (blue Democrat, red Republican).
