We previously looked at Brier scores for The Economist’s 2020 Presidential model predictions over time, and surprisingly found the scores worsened closer to Election Day. Given the closeness of their predictions, I assumed FiveThirtyEight’s Brier scores would trend the same way but was wrong again. In the chart below you can see Brier scores for […]
How did FiveThirtyEight’s model perform over time? Read More »
PredictIt is a U.S.-based prediction market and SBK is a British sports betting app, but both are indicating that political gamblers see Republicans making gains in the U.S. Senate this year (at least as of Friday, February 4, 2022). The probabilities in the 12 Senate races where both platforms are currently accepting action are extremely
PredictIt and SBK forecasting Republican Senate gains in 2022 Read More »
As discussed in an earlier post, as of the morning of Election Day 2020, The Economist’s presidential forecasting model had a slightly higher Brier score (lower = better, higher = worse) than FiveThirtyEight’s model, but each model correctly predicted the outcome in the same number of states (49 out of 51). This made me curious
In the summer of 2020, online trash talking between FiveThirtyEight’s Nate Silver and The Economist’s G. Elliot Morris sparked the “Model Wars.” Now that the dust has settled, I’m comparing the Brier scores and the number of correctly called states from their final state-level model outputs on November 3, 2020. Please note that the models
Who won the 2020 Model Wars? Read More »
Election forecasting models took a hit to their credibility for missing Donald Trump’s victory in 2016 but were generally accurate in 2020. Because these models are dependent on polling, we can probably expect to see future issues with forecasting elections as pollster response rates drop, households disconnect their landlines, and social trust declines. At the
Were gamblers more accurate than the forecasting models in 2020? Read More »
