Sunday, November 7, 2021

New Jersey pollster publishes apology to NJ voters for misleading final Governor’s poll giving Democrat Murphy 11 point lead. Murphy had only a 1 point lead over Republican Ciattarelli when election was finally called

 .

Democrat Phil Murphy led by 1 point when the race was called Wednesday evening with 99% of the vote in. Monmouth’s last poll had Murphy up by 11.

Fri., 11/5/21, “I blew it”: New Jersey pollster apologizes after close governor’s race," Axios, via news.yahoo.com

“Patrick Murray, director of the Monmouth University Polling Institute on the Jersey Shore, wrote an op-ed [posted below] for The (Newark) Star-Ledger apologizing for a poll six days before the election that said Gov. Phil Murphy “maintains a sizable lead” over Republican Jack Ciattarelli.

Why it matters: The poll had Murphy up by 11. The race wasn’t called until Wednesday evening. With 99% of the vote in, Murphy is up by 1 point.

What they’re saying: Murray, who has headed polling since 2005, writes that if you’re “a Republican who believes the polls cost Ciattarelli an upset victory or a Democrat who feels we lulled your base into complacency, feel free to vent. I hear you”:

I owe an apology to Jack Ciattarelli’s campaign–and to Phil Murphy’s campaign for that matter–because inaccurate public polling can have an impact on fundraising and voter mobilization efforts. But most of all I owe an apology to the voters of New Jersey for information that was at the very least misleading.”

What we’re watching: “If we cannot be certain that these polling misses are anomalies,” the pollster writes, “then we have a responsibility to consider whether releasing horse race numbers in close proximity to an election is making a positive or negative contribution to the political discourse.””

“Go deeper...By the numbers: N.J. close call"

…………………………………

Added: 11/4 and 11/5/21, Pollster: ‘I blew it.’ Maybe it’s time to get rid of election polls. | Opinion, By Patrick Murray

“Patrick Murray, director of the Monmouth University Polling Institute, says the growing perception that election polling is broken cannot be easily dismissed.”

I blew it. The final Monmouth University Poll margin did not provide an accurate picture of the state of the [NJ] governor’s race. So, if you are a Republican who believes the polls cost Ciattarelli an upset victory or a Democrat who feels we lulled your base into complacency, feel free to vent. I hear you.

I owe an apology to Jack Ciattarelli’s campaign–and to Phil Murphy’s campaign for that matter–because inaccurate public polling can have an impact on fundraising and voter mobilization efforts. But most of all I owe an apology to the voters of New Jersey for information that was at the very least misleading.

I take my responsibility as a public pollster seriously. Some partisan critics think we have some agenda about who wins or loses. I can only assume they have never met a public pollster. The thing that keeps us up at night — our “religion” as it were — is simply getting the numbers right.

Unlike a campaign consultant, my job is not to figure out a candidate’s best path to victory, but to provide an explanation of the public mood as it exists now. Polling continues to do that quite well when we are taking a snapshot of the full population. For example, polls on the impact of COVID and attitudes toward vaccines over the past year and a half provided an accurate picture of shifting behaviors that directly impacted [government mandates about alleged] public health.

Election polling is a different animal, prone to its fair share of misses if you focus only on the margins. For example, Monmouth’s polls four years ago nailed the New Jersey gubernatorial race but significantly underestimated Democratic performance in the Virginia contest. This year, our final polls provided a reasonable assessment of where the Virginia race was headed but missed the spike in Republican turnout in New Jersey.

The difference between public interest polls and election polls is that the latter violates the basic principles of survey sampling. For an election poll, we do not know exactly who will vote until after Election Day, so we have to create models of what we think the electorate could look like. Those models are not perfect. They classify a sizable number of people who do not cast ballots as “likely voters” and others who actually do turn out as being “unlikely.” These models have tended to work, though, because the errors balance out into a reasonable projection of what the overall electorate eventually looks like.

Monmouth’s track record with these models, particularly here in our home state over the past 10 years, has been generally accurate within the range of error inherent in election polling. However, the growing perception that polling is broken cannot be easily dismissed.

Monmouth’s conservative estimate in this year’s New Jersey race was an 8-point win for Murphy, which is still far from the final margin. More than one astute observer of polls has pointed out

that the incumbent was consistently polling at either 50% or 51% against a largely unknown challenger. That metric in itself should have been an indication of

Murphy’s underlying weakness as an incumbent.

Still, in the age of polling aggregators, needles, and election betting markets, we tend to obsess more on the margin than on the candidate’s vote share. And we end up assuming that the “horse race” number is more precise than it actually is. This can lead to misleading narratives about the state of the race, as happened in New Jersey this year.

While pundits and the media are hardwired to obsess on margins, we pollsters bear some responsibility too. Some organizations have decided to opt-out of election polling altogether, including the venerable Gallup Poll and the highly regarded Pew Research Center, because it distracts from the contributions of their public interest polling. Other pollsters went AWOL this year. For instance, Quinnipiac has been a fixture during New Jersey and Virginia campaigns for decades but issued no polls in either state this year.

Perhaps that is a wise move. If we cannot be certain that these polling misses are anomalies then we have a responsibility to consider whether releasing horse race numbers in close proximity to an election is making a positive or negative contribution to the political discourse.

This is especially important now because the American republic is at an inflection point. Public trust in political institutions and our fundamental democratic processes is abysmal. Honest missteps get conflated with “fake news”–a charge that has hit election polls in recent years.

Most public pollsters are committed to making sure our profession counters rather than deepens the pervasive cynicism in our society. We try to hold up a mirror that accurately shows us who we are. If election polling only serves to feed that cynicism, then it may be time to rethink the value of issuing horse race poll numbers as the electorate prepares to vote.”

“Patrick Murray is the director of the Monmouth University Polling Institute.”

…………………………………

Added: Skew of sample, ie, D/R/I, not mentioned in these articles. Margin of error in one poll was 4.1:

11/6/21, Why the pollsters were so wrong about the N.J. governor’s race," nj.com

“Gov. Phil Murphy took the stage inside Asbury Park’s Grand Arcade at about half-past midnight Wednesday morning to give a four-minute speech thanking his dwindling number of supporters in the room for sticking through the night.

It was supposed to be a victory speech, his staff thought confidently hours earlier. Instead, moments after Murphy left the stage, the music that had played on repeat for five hours shut off and the dark hall turned bright at the flick of the switch to massive floodlights, and the dejected crowd went straight toward the exit.

Hours earlier they were jubilant. Why? Public polling showed Murphy was a shoo-in to become the first Democrat since Brendan Byrne in 1977 to win a second term in the Garden State.

Instead, the results throughout Wednesday showed the governor and Republican Jack Ciattarelli separated by less than a percentage point. The Associated Press declared Murphy the winner Wednesday

by a less-than-1-percentage-point margin, nearly 24 hours after the polls closed.

So what happened with all those polls?

“In the past, we’ve been very good at that modeling, but in the (Donald) Trump era that is going out the window,” said Patrick Murray, director Monmouth University Polling, which released a survey last week that showed Murphy beating Ciattarelli by 11 percentage points.

Monmouth, like other polls released during the campaign, has a proven track record.

In 2017, it released a poll within a week of Murphy’s matchup against Republican nominee Kim Guadagno that showed Murphy winning by 14 points. Murphy won by 14 points. 
 
In 2013, it had then-Gov. Chris Christie ahead of his Democratic rival by 20 points. Christie won by 22. And so on.
 
It has an “A” rating from FiveThirtyEight, which keeps tabs on pollsters’ track record. 
 
Asking people their thoughts on things like mask mandates, climate change, and other public policy gives pollsters a clear snapshot in time of how people feel about certain issues. Pollsters like Murray haven’t run into problems with those types of surveys.

But elections? They don’t always hit the mark as of late.

“A significant number of Trump Republicans came out to vote but were not captured in our polling,” Murray said. “Polling, the media. They’re all part of an establishment they distrust and so they won’t bother to speak to us, and it’s large enough now, [allegedly] kind of activated by Donald Trump, that it is throwing off a lot of our polling around elections.” [It's important to mention that "distrust" wasn’t “activated” by Trump, and further that Trump himself embraced the establishment immediately after being elected. The views of voters you cite have been informed by many years of experience not involving Trump, mainly with the Republican Establishment].

And it wasn’t just Monmouth.

A Rutgers-Eagleton survey released Monday had Murphy with an 8-point lead. Fairleigh Dickinson University survey had him up by 9 percentage points, the same margin as a Stockton University survey. An Emerson College/PIX 11 survey released late last month showed it at a 6-point advantage for Murphy and the Republican-leaning Trafalgar Group showed the closest margin–4 percentage points.

Ashley Koning, director of Eagleton Center for Public Interest Polling, stressed the human element of polling people as politics are increasingly more polarizing. [“Polarizing?” If everyone thinks alike, isn’t that communism?]

“There needs to be a better education of what polls are and what polls aren’t,” Koning said. [It’s a little late for that] “No. 1, they aren’t crystal balls. No. 2, they are snapshots in time. No. 3, they’re based on human behavior and perceptions. And people can lie. Maybe there was something going on with Republicans not participating in polls.”

She noted her [Eagleton] poll [predicting Murphy by 8 points]. She noted her poll had a 4.1 percentage point margin of error.

“That really shows there was a wide range that could have happened,” Koning said. “We need to be doing a better job showing that range of possibility and embracing that uncertainty. The media and the public need to be a better job of being a poll consumer and not putting all the eggs in one basket. There will always be error there because we can’t talk to an entire population.”

The election’s numbers, of course, aren’t final. Thousands of votes, including mail-in and provisional ballots, are still being counted in New Jersey as the state adjusts to more people voting in non-traditional ways. And many of the outstanding votes are mail-in, a system Democratic voters are more likely to use. That could boost Murphy’s margin in the end.

Lindsey Cormack, an assistant political science professor at the Stevens Institute of Technology in Hoboken, argues people need to get “to a place where we have to release our hopes as to what polls can tell us.” [Who is “we?”]

She noted landline polling is becoming “extinct” and that cell phone polling is “difficult.”

”This follows that pattern: We think we know what’s going until we don’t,” Cormack said.”

……………………………………..

New Jersey trivia: 3/31/21, “New Jersey easily ranks as one of the most racially and culturally diverse states in the country. In fact, nearly one in four residents were born outside the United States."Patrick Murray, Monmouth.edu

 

.................

 

No comments: