AtlasIntel had the best performance across all pollsters of the 2020 US Presidential Election with an average error of 2.01p.p. Our final national-level poll showing Biden with a 4.7 p.p. advantage is likely to be the single most precise estimate of the US popular vote. AtlasIntel also conducted the most precise polls across all pollsters for the states of Michigan and North Carolina. In all states polled by AtlasIntel, results fell within the margin of error of our estimates. The AtlasIntel average error was not only lower than that of other pollsters, but also lower than that of polling averages and model-based polling aggregators (see figures below):

Earlier in the 2020 election cycle, AtlasIntel provided the most accurate forecasts of the Democratic Primary races by average RMSE, including the single best polls of New Hampshire, California, and Florida.

This unparalleled performance is a testimony of the quality of our methodology and the robustness of our innovative data collection approach. All of AtlasIntel polling in the United States has been conducted online, disproving long-standing arguments regarding the superiority of live-caller telephone interviews.

Atlas Tracking PRO, our flagship polling product for private subscribers, will continue to undergo significant improvements in the aftermath of the election, with new indicators related to consumer confidence and economic expectations scheduled to be released during the next 60 days.

 

Pollster Error in the 2020 US Presidential Election

[Based on difference between the lead of the winning candidate and poll estimates]

 

AtlasIntel Error in the 2020 US Presidential Election vs. Forecasters

[Based on difference between Joe Biden’s and Donald Trump’s final vote share and poll/forecast estimates]