Key points are not available for this paper at this time.
This study uses multiple regression to analyze more than 1600 state and nationwide polls released from April to November 2020 concerning the U.S. Presidential election of that year. The study finds that sample composition and survey-taking technology affected the results of these polls. Specifically, polls that over-sampled Democrats and polls that used live-callers were biased in favor of Biden. Live-caller bias almost certainly argues that polls suffered from Shy Trumpers. In addition, many poll-takers are found to be biased relative to a reference set of polls, independent of sample composition and the use of live-callers.
Clifford F. Thies (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: