The pollsters who predicted the US presidential election vote wrongly by giving Joe Biden a large lead over current President Donald Trump during the final week before the election, are the ones who did not “weight” the sample’s voters or who underestimated Republican turnout, The Washington Times reported.
Some firms went instead with how the surveyed voters identified themselves by party with no adjustment, or “weight,” based on previous elections, said the Times.
According to a recent Pew Research Center analysis, “it’s clear that national and many state estimates were not just off, but off in the same direction: They favored the Democratic candidate.”
While Republicans represented 33% of the vote in 2016, some polls predicted that they won't be more than 30% in 2020. The actual 2020 Republican turnout was 36% – the same 3% difference but in the opposite direction.
This explains why Republicans are currently protesting against news media and university pollsters, saying that the wrong estimates of 2020 polls hurt their voter turnout and incited persistent negative commentary from the national press obsessed with polls.
“After this election, I think the polling industry needs to take a hard look at what it does,” reelected Republican Sen. Susan Collins of Maine told Fox News when all polls were predicting she would lose.