The Economist: “Even after correcting for demographic biases, pollsters’ data can still be unrepresentative. They may have the right shares of Latino voters and boomers, but nevertheless have too many Republicans or Democrats. This concern is pronounced when an event causes especially good, or bad, news for a political party. At such times surveys can suddenly be swamped with partisans who are eager to voice their love, or hate, for the president.”

“In the wake of Mr Trump’s acquittal in the Senate, pollsters suspect that such a bias could be affecting polls. Courtney Kennedy, the director for survey research at the Pew Research Center, says that there is a ‘strong possibility’ that the recent uptick in Mr Trump’s ratings has a wave of optimistic Republicans as its source. She says that outlets can control this problem by adjusting their data to have the correct shares of Democratic- and Republican-leaning voters, but the idea is relatively new and few pollsters have data good enough to perform such corrections.”

“The Economist’s analysis of polls taken during Mr Trump’s impeachment proceedings affirms Ms Kennedy’s suspicion. In polls that weight their data to represent America’s partisan balance or the results of the 2016 election, the share of adults who approve of Mr Trump’s job as president has risen by half a percentage point since impeachment proceedings began in earnest last October. But in polls that do not, Mr Trump’s ratings have increased by over three percentage points.”

Gabe Fleisher has an interesting interview with pollster Ann Selzer and why she’s been so successful at polling the Iowa caucuses.

The bottom line: Selzer doesn’t try to model likely turnout in future caucuses based on past voting behavior: “We ask everybody who is a registered voter if they’re likely to caucus on the Democratic side, no matter whether they are registered Democrat, Republican, or Independent. We ask all of them.”

“In 2008, that meant her final pre-caucus poll projected that a “jaw-dropping” 60% of caucus-goers would be first-time participants in the primary process. That prediction received widespread skepticism, but on caucus night, 57% of attendees were new participants, fueling Obama’s upset — and cementing Selzer’s reputation.”

Selzer calls her approach “polling forward.” She explains: “Had I done anything that looked backward at what happened before, I would have been blinded from seeing what was coming in the future… Other people will weight their data to look like past caucusgoers and other sorts of things or decide that it’s really only registered Democrats that matter, that they don’t mind losing what might be happening with others. But if something big is happening, they won’t see it. They will be quite literally blinded to it.”

Matthew Yglesias digs into yesterday’s poll showing top Democrats leading President Trump in Georgia and notes “the fine print on the poll contains a sentence that should be a huge red flag to contemporary consumers of political polling: The data are weighted based on race, age and sex to accurately reflect the demographics of the state.”

“There’s nothing wrong with weighting your sample based on race, age, and sex to match the demographics of the state. That’s standard practice in the industry. The problem is what the poll didn’t weight on — educational attainment. Many state-level polls omitted this factor in 2016, leading them to underestimate Trump’s strength in key swing states. The most responsible pollsters responded to 2016 by making sure to improve their weighting. But many pollsters — especially those doing state-level polling — continue not to weight by education.”

“This failure to weight not only leads to errors (which could be compensated for by averaging), it leads to systematic bias against Trump and the GOP, meaning everyone who publishes or disseminates unweighted polls ends up contributing to misinformation about the real state of American politics.”

Nate Silver: “A common refrain in coverage of the Democratic primary campaign is that the race looks much different in the early states than it does nationally, with a wider playing field, greater strength for upstart candidates such as Pete Buttigieg, and signs of weakness for the leader in national polls, Joe Biden.”

“The refrain is true if you look only at Iowa or only at New Hampshire, but it’s mostly not true overall. Taken collectively, polls in the four early states — Iowa, New Hampshire, Nevada and South Carolina — tell almost the same story as national polls: Biden leads, Elizabeth Warren is in second, Bernie Sanders is in third, and Buttigieg is still a fairly distant fourth.”

Nate Silver: “Much maligned for their performance in the 2016 general election — and somewhat unfairly so, since the overall accuracy of the polls was only slightly below average that year by historical standards — American election polls have been quite accurate since then. Their performance was very strong in the 2018 midterms, despite the challenge of having to poll dozens of diverse congressional districts around the country, many of which had not had a competitive election in years. Polls have also generally been accurate in the various special elections and off-year gubernatorial elections that have occurred since 2016, even though those are also often difficult races to poll.”

“Does that mean everything is looking up in the industry? Well, no. We’ll introduce some complications in a moment. But I do want to re-emphasize that opening takeaway, since the media is just flatly wrong when it asserts that the polls can’t be trusted. In fact, American election polls are about as accurate as they’ve always been.”

President Trump blasted Fox News over their latest poll showing the majority of Americans now showing support for impeaching and removing him from office.

Said Trump: “From the day I announced I was running for President, I have NEVER had a good Fox News Poll. Whoever their pollster is, they suck.”

He added: “But Fox News is also much different than it used to be in the good old days… Fox News doesn’t deliver for US anymore. It is so different than it used to be. Oh well, I’m President!”

Mark Blumenthal: “The impeachment story is blowing up. It’s a high-stakes moment — for President Trump, for Democrats and for pollsters. It’s also a scary moment for polling.”

“Yes, people who follow politics are now intensely interested in whether the latest developments might shift public opinion about Trump and impeachment. But when news is exceptionally big, a growing body of evidence suggests it can throw off the accuracy of polling itself.”

The Economist: “In its latest software release, Apple has made it possible for iPhone users to send all unknown callers to voicemail automatically. Although the feature will no doubt prove useful to the millions of customers whose peaceful suppers are ruined by fake calls, it could be disastrous for the faltering public-polling industry.”

“The challenges telephone pollsters face have been growing. Polling by phone has become very expensive, as the number of Americans willing to respond to unexpected or unknown callers has dropped. Back in the mid-to-late-20th century response rates were as high as 70%, according to SSRS, a market research and polling firm. But the Pew Research Centre estimates that it received completed interviews from a mere 6% of the people it tried to survey in 2018.”

Monmouth pollster Patrick Murray acknowledged that a poll released this week showing Joe Biden’s support dropping by 13 percent was an “outlier.”

Murray said the result was the “product of the uncertainty that is inherent in the polling process” which “occurs very infrequently.”

He added: “In the end, we must put out the numbers we have. They should always be viewed in the context of what other polls are saying, not only as it applies to the horse race, but also for our understanding of the issues that motivate voters in their decision-making process.”