The original goal of the PollyVote project was to demonstrate advances in forecasting research by applying them to election forecasting. In particular, the PollyVote strictly adheres to two of the most important principles derived from forecasting research:

  1. Combine forecasts from different methods that use different information.
  2. Keep it simple: There is no evidence that complexity improves accuracy.

The line chart above shows how the PollyVote’s forecast of the national popular two-party vote for the 2016 election has developed over time. You can also compare this forecast to forecasts from other components by expanding the table (‘+’) and selecting the respective method using the checkboxes. The second chart shows the latest forecast of the Electoral College.