NYT Admits Pollsters Overestimating Democrat Candidates Due to ‘Persistent and Unaddressed Biases’

Pollsters could be overestimating the strength of Democrat senate candidates with “persistent and unaddressed biases in survey research,” the New York Times reported Monday via data analysis.

The data was assembled by analyzing and comparing the 2016 and 2020 elections, which created a “poll error” that reveals Democrat Senate candidates in the 2022 cycle “are outrunning expectations in the same places where the polls overestimated Mr. Biden in 2020 and Mrs. Clinton in 2016.” The overestimated Democrat expectations match polling failures in previous elections.

The states where pollsters in 2022 could be overestimating Democrat strength are in key races that will determine which party controls the Senate. They include Ohio, Pennsylvania, Arizona, Georgia, and Wisconsin. Polling in all five states remains very tight, besides Ohio, where President Joe Biden has one of the worst approval ratings.

[W]arning sign is flashing again,” the Times wrote about previous polling. “It raises the possibility that the apparent Democratic strength in Wisconsin and elsewhere is a mirage — an artifact of persistent and unaddressed biases in survey research”:

If the polls are wrong yet again, it will not be hard to explain. Most pollsters haven’t made significant methodological changes since the last election. The major polling community post-mortem declared that it was “impossible” to definitively ascertain what went wrong in the 2020 election.

…

Wisconsin is a good example. On paper, the Republican senator Ron Johnson ought to be favored to win re-election. The FiveThirtyEight fundamentals index, for instance, makes him a two-point favorite. Instead, the polls have exceeded the wildest expectations of Democrats. The state’s gold-standard Marquette Law School survey even showed the Democrat Mandela Barnes leading Mr. Johnson by seven percentage points.

But in this case, good for Wisconsin Democrats might be too good to be true. The state was ground zero for survey error in 2020, when pre-election polls proved to be too good to be true for Mr. Biden. In the end, the polls overestimated Mr. Biden by about eight percentage points. Eerily enough, Mr. Barnes is faring better than expected by a similar margin.

As a result, the Times noted that David Wasserman’s Cook Political Report midterm predictions could be faulty if the polls turn out to be as wrong as they were in 2020. Wasserman, who is esteemed among the elites in Washington, D.C., has been hyping the Democrats’ chances of staving off a red wave come November. In recent weeks, Wasserman has updated several races to lean left toward Democrats.

But just like other pollsters in previous years, the Cook Political Report has been wrong. In 2020, the Cook Political Report predicted Republicans would lose up to 15 House seats to add to their 34-seat majority, but the estimate was 29 seats off. Instead, Republicans gained 14 House seats and the Democrats entered 2021 with a narrow 222–213 House majority.

Wasserman’s latest 2022 predictions are in part based on the abortion issue, which the Times argued may be factoring into “signs of nonresponse bias — when people who don’t respond to a poll are meaningfully different from those who participate — creeping back into their surveys.”

On Monday morning, Wasserman tweeted the Times article and was notably quiet about its grim findings. “Those surprisingly strong polls for Dems you see in the same states where 2020 polls overestimated them? Probably another mirage,” he tweeted.
Follow Wendell Husebø on Twitter @WendellHusebø. He is the author of Politics of Slave Morality.