Tag Archive: polls

Polls: Headline vs. Bottom Line

“Gov. Christie’s job approval rating improves to 51 percent.

Christie [gets] high marks for holding the line on spending.”

          – Star Ledger
headline and lead sentence on

            Fairleigh Dickinson Poll – October 12, 2010

Polls: love ’em or hate ’em, but there is also more than one way to read ’em. A trend analysis which takes a longer view and accounts for changes in both approval and disapproval on the above two matters – Christie’s approval rating and holding the line on spending – provides a significantly different opinion than that which the newspaper heralds.

The governor’s approval rating has ranged from 52% to 43%. Since March 3, 2010, the reporting date of the first Fairleigh Dickinson poll after Christie took office, his approval rating worsened 1%, from 52% on March 3 to 51% now. His disapproval rating worsened 16%, from 21% to 37%. The net total damage to his approval is 17%. As time went on more respondents left the “unsure” or “I do not know” category and joined the disapproval category.

Since March 3 on the issue of “the state should hold the line on spending even if many programs are reduced,” Christie’s position worsened by 6%, from 66% on March 3 to 60% now. On the opposite issue of “the state should raise taxes if necessary and continue to support state programs,” the governor’s position worsened by 1% from 21% to 22% – net damage to his position 7%.

In spite of the fact that 51% approve his job performance and 60% support holding the line and reducing programs, the current trend is not favorable to Governor Christie. Be not of faint heart. The headline in this case may be positive for him but the bottom line trend is less so.  

Adler-Runyan Poll: Yes, it’s a toss-up

The Monmouth University/Gannett New Jersey Press Media Poll (PDF) have given us the second poll of New Jersey’s Third Congressional District this week, and it looks just like Eagleton’s (41-39) poll :

More voters approve than disapprove of the job freshman Congressman John Adler is doing, but enough voters are looking for change in Washington that challenger Jon Runyan is within striking distance.

With five weeks to go before Election Day, the poll of likely voters found the incumbent with a narrow lead within the poll’s margin of error – 42% for Democrat Adler to 39% for Republican Runyan, with 13% undecided. Adler leads by 48% to 35% in the Burlington and Camden Counties portion of the district, while Runyan has a 44% to 34% advantage among Ocean County voters.

In related questions, Adler’s job approval is 49-34.  DeStefano is at 4%.  Click through to see various breakdowns on issues, which are all pretty even.  (Also, see third poll below the break.)

Adler-Runyan race is a toss-up

Swing State Project points us to this research poll of NJ3 (PDF) for the Rutgers-Eagleton Institute of Politics.

Professor Redlawsk tells us on his blog:

Still, as the release below shows, Adler is in reasonable position for an incumbent Democrat in a marginal seat given the prevailing winds of 2010. He seems to be so because most likely voters in the district actually say they prefer experience over an outsider and because he is seen somewhat more favorably than is his opponent Republican Jon Runyan.

He has a detailed discussion of the likely voter screen. The likely voter sample is 41-39-6 for Adler-Runyan-DeStafano. Adler has a nine point lead 40-31-6 with registered voters. Turnout looks to be killing Democrats, as Obama’s twitter feed suggested yesterday:

The other side is counting on you staying home this Nov. They’re counting on your silence. They are betting on your apathy. Prove them wrong

Polls and the Adler-Runyan Race

We’re fortunate that Rutgers Professor David Redlawsk has arranged for the first independent poll of poll of the NJ3 Congressional Race, widely believed to be the most (only?) competitive one this year. Incumbent John Adler, who has positioned himself as a conservative Democrat, faces Jon Runyan, who is a famous football player but so far seems to know very little about policy. The full PDF is available here. The headline is that Representative Adler leads in the poll, although with only 421 registered voters the margin of error is an uncomfortably larger 4.8 percent.

Likely Voters: Adler 40, Runyan 30, Don’t Know 22, Won’t Vote in this race 8

Registered Voters: Adler 35, Runyan 28, Don’t Know 23, Won’t Vote 13

There are other permutations of the question, but I think these are two most important. On the one hand, Adler is ahead. On the other, he is way under 50%, a sign of danger for an incumbent. In July, Adler released an internal poll where he lead by 17 (51-34)  Statistically, such poll announcements favor the releaser by an extra 6-7% or so.  (That is, Adler or Runyan would only release polls that happen to show unusually large/lucky leads, while our faithful Professor releases all results.)  17-7=10, so you might call the polls in good agreement with my proposed correction. Runyan has not released anything, so it now does seem likely Adler is ahead.

Other “generic” polls of New Jersey suggest that other Democratic incuments should be fine:

Monmouth: Own Congressman Favorable-Unfavorable: 54 – 28 (July)

Rutgers Democratic Districts: 41-22 (February)

Rutgers Statewide Generic: 33-31 (February)

FDU Statewide Generic: 47-39 (February)

Nationally the picture is more grim. In 2008, Democrats nationwide won the House vote by 8.9% They are currently trailing nationwide by 4.7% according to TPM’s Poll Tracker calculation. Obama won NJ3 52-47, and Adler won 52-48. A twelve point swing would obviously bring Runyan to victory, and indeed Christie did win the district according to Redlawsk.  On the other hand, the latest NBC/WSJ poll shows a huge (55-30) lead for Democrats in the Northeast, so the devastating swings may be elsewhere.  

Hey FDU, how about a real poll on “spending”?

A new FDU/Public Mind poll was released today that trumpets how New Jerseyans want to “hold the line on spending”, and then spends the first three paragraphs of their summary discussing this, even though there were a mere two questions on the state budget in the poll.  What makes this worse is that one is the generic “how much have you heard about the state budget?” and the other is a loaded question in light of Governor Christie publicly bashing all spending and government programs, teachers unions, and anything related to public employees for the past 6 months.

It would be nice if FDU actually asked questions that got to the substance of the state budget issue before a declaration that New Jersey voters want to “hold the line on spending”.  For example, the one question asked the following loaded frame:

In order to balance the budget, some people say the state should hold the line on spending even if many programs are reduced.  Others say to balance the budget the state should raise taxes if necessary and continue to support state programs.  Which position comes closest to your view?

Now, this is a load of crap in terms of a question.  What “some people are saying” is that taxes on the state’s wealthiest should not be cut at the expense of these programs.  What “some people are saying” is that there shouldn’t be a corporate tax cut at the expense of these programs.  What “some people are saying” is that there shouldn’t be a $1 BILLION tax cut at the expense of cutting programs for seniors, for women’s health, for cutting public transportation services, for cutting education funding or for raising fees for just about everything (but don’t call it a tax, of course).

What I want to see is a poll that asks the following questions in terms of Christie’s choices and the budget:

  • Are you ok with having less garbage collection/less snow removal/slower emergency response time at the expense of lower taxes on the state’s highest earners?
  • Are you ok with having higher fees for public transportation and lower levels of essential services so that those earning over $400,000 can enjoy a tax break?
  • Do you think that those earning over $1,000,000 deserve a tax cut in this economic climate?
  • Are you in favor of eliminating services such as auto inspections if it means a greater likelihood of dangerous automobiles being on the roads?
  • Given the recent scandals with private debt collectors and the NJ tax department, are you in favor of an initiative to privatize other debt collection services?

Those are just a few of the many real and true questions that should be asked of NJ voters when it comes to what Governor Christie is choosing to do in this state.  When the corporate media is stretched thin and the signal-to-noise ratio is extremely low and the Governor has the biggest bully pulpit to act the part, most voters don’t know what is actually going on.

And the voters are being done a disservice when they are being polled with loaded questions that don’t explain just what is being done to them.

How 538 Rates New Jersey Pollsters

Nate Silver at FiveThirtyEight.com has put out a new set of pollster rankings (methodology here and reponse to complaints here) and I notice our New Jersey pollsters did off pretty well. His “Pollster Induced Error” (PIE) statistics is meant to capture “the amount of error that a pollster introduces above and beyond that which is unavoidable due to things like sampling variance. The lower a firm’s PIE the better.” Farleigh Dickinson (1.75), Rutgers (1.76), and Gannett/Monmouth (2.17) are all better than the default rating. Ratings are primarily based on how well polls within the last 21 days predict the outcome of the election over the last decade.  

I should note, though, there is a statistical correction (“reversion to the mean”) in which:

…the ratings for polling firms which were members of NCPP, or which had signed onto the AAPOR Transparency Initiative, as of June 1, 2010, are regressed toward a different mean than those which hadn’t. Essentially, then, polling firms are rewarded for having made a public commitment to disclosure and transparency — but the basis for rewarding them is statistical rather than ideological.

FDU and Rutgers both have met this criterion, but to my surprise

Gannett/Monmouth (according to 538) has not, and so I imagine it suffers slightly in this rating system. If this is an error by Silver, Patrick Murray might want to correct it. There certainly seems to me to quite good details in their releases.  

New Survey USA Poll has Christie at 63% disapproval

Survey USA is out with a new poll that shows Governor Christie’s approval rating upside down. Here’s the report from ABC 7:

The Governor stands at 33% approval, 63% disapproval, but he says he could care less. I don’t see the poll posted on their website yet, but I’ll put it up when they do. It didn’t take very long for voters to get buyers remorse. Then he went on to say this:

“Almost everyone of those polls said I wasn’t going to win too, well, here I am,” said Governor Christie.

Actually as I remember it, Christie led nearly the whole way with the polls closing at the end. Funny, thats how Pollster.com remembers it too. Out of 86 polls taken between October 2008 and November 2009, only 19 of them ever showed Corzine leading Christie. He’s said he’s not good at math, but I don’t think that 22% of the polls is almost ever one.

Monmouth and Rutgers Polls on the Budget

We’re lucky to have poll releases today from Monmouth/Gannett (full PDF) and Rutgers Eagleton (full PDF) on New Jersey budget issues. Some of the Eagleton results were released earlier in the week. I’ll mention the FDU poll which is about a month older, but still after the budget speech, and which is more favorable to Christie. In fairness, you should also keep in mind that Governor Corzine’s budget proposals were not very popular either.

First, Governor Christies’ approval rating is going down in all polls:

Monmouth: 41% approve, 43% disapprove (all adults; 42-44 registered voters)

Eagleton: 33% favorable, 37% unfavorable, (all adults)

FDU: 43% approve, 32% disapprove

On the Christie budget:

Monmouth: 22% satisfied, 32% “can live with it,” 44% dissatisfied

Ealgeton: 13% “very pleased,” 30% “pleased,” “21% somewhat displeased,” “29% very displeased”

FDU poll: 38% favorable, 39% unfavorable.

The Eagleton poll asked about what areas should be cut. If you suspect the public likes government spending and dislikes taxes you won’t be surprised by their conclusions:

“Our recent poll showed that half of New Jerseyans are displeased with Governor Chris Christie’s proposed budget,” said David Redlawsk, director of the Rutgers-Eagleton Poll and professor of political science at Rutgers University. “These new results give a good sense of residents’ priorities in this difficult time. Laying off teachers or significantly cutting school aid are not seen as solutions. On the other hand, given today’s economic challenges, people do not want to see their own costs increase either. The state is between a rock and a hard place, with clear support for a limited number of solutions, one of which is cuts to municipal government.”

The public also opposes cuts to aid for the poor in the Eagleton poll, and state colleges scored nearly as well as public (K-12) schools.  Here’s the quote from the Monmouth release:

“The local aid reduction, particularly to schools, was always going to be the flashpoint for criticism of the plan, and the governor’s clash with the NJEA only increased the heat. If part of his strategy was to win over public opinion, it hasn’t been an overwhelming success,” said [Monmouth pollster] Murray.

One contradiction between the two polls is that Monmouth asked about “cuts in aid to local school districts and towns” which the public denounced as unfair. Eagleton asked about schools, towns, and other possibilities separately, so it found school cuts unpopular but municipal cuts supported. On the other hand, Monmouth also picked up that more voters say they will vote against school budgets than vote for them which you might consider a little inconsistent.  

The timing of my calling bull$h!t on Sen. Kean is just “happenstance”

As Hopeful notes below, a new poll by FDU shows (1) a dead heat between Senator Menendez and Tom Kean, Jr. for a race that is over two years from now, and (2) a very mixed bag on what people in NJ think about health care reform.  

As Hopeful notes, 42% of New Jerseyans think that they personally will be worse off if the current health care reform bill passes, while 37% feel that they personally will be better off if the current health care reform bill passes.  However, that 5% spread is reversed when the question is asked about the country as a whole, with a 45% – 40% margin indicating that the current health care bill will be better for the country.  Adding to this, there is a 5% margin (40% against, 35% for, 25% don’t know) when it comes to whether respondents would urge THEIR member of Congress to vote for or against ANY health care bill.

In response to all of this, Kean finds the one way to interpret these numbers that is made up of fairy dust:

“Our United States Senators should finally listen to the majority of New Jerseyans  and support a fresh approach to reforming our health insurance industry.”

What’s more, Kean said that the suspicious timing of his pontificating was merely “happenstance”.

Now, say what you want about the current health care bill – there certainly is more than enough things to like and dislike about the bill on an individual level, but the one thing that can NOT be said is what Kean is asserting about “a fresh approach”.  It is either (1) is this bill good for me, (2) is this bill good for the rest of the country or (3) do you want your Congressman to vote for ANY bill.  If Kean wants to be taken seriously, then he should actually say things that are accurate – especially when it comes to issues that he claims to represent “the majority of New Jerseyans” on and issues where he hopes to represent all of New Jerseyans.

When reached for comment, Adam L a/k/a clammyc noted that the timing of this post was merely “happenstance”.

Incumbents and that 50 Percent Poll Rule

I wanted to bring your attention to an interesting post by Nate Silver of 538.com on The Myth of the Incumbent 50% Rule. He’s prompted by the claim that incumbents get only the same percentage of the vote as they do in early polling, and therefore incumbents under 50% almost always lose. Here’s his conclusion:

1) It is extremely common for an incumbent come back to win re-election while having less than 50 percent of the vote in early polls.

2) In comparison to early polls, there is no demonstrable tendency for challengers to pick up a larger share of the undecided vote than incumbents.

3) Incumbents almost always get a larger share of the actual vote than they do in early polls (as do challengers). They do not “get what they get in the tracking”; they almost always get more…

It is probably OK to focus on an incumbent’s vote share in early polls while downplaying the challenger’s number, but if you do, you need to add 6-7 percent to it to have the most accurate prediction of his likely performance in November.

Silver’s data, which you can see by clicking through, shows that incumbents who poll 45% in January-June usually win — like Frank Lautenberg in 2008, at only 45.7%, who got to 56% on election day — and overall 19 of 30 incumbents under 50% end up winning. (Incumbents over 50% are safe.) In short, undecideds do not usually break overwhelmingly to the challengers as conventional wisdom tell us. Mark Blumenthal of Pollster.com says Nate is right, and explains that the “myth” is largely based on old races. I recall, but can’t find the link, that kos recently found half of incumbents polling under 50% lose and half win. Many Democratic learned this lesson in the 2004 Presidential election, where Bush won despite many polls putting him under 50%. Here in New Jersey, Menendez won despite being below 40% (though he was appointed) and Corzine lost, but did get that 7 point surge.

I can’t help but wonder if this speaks to the famous New Jersey election effect — that Democrats poll too low. Perhaps instead of looking for a Jersey explanation, it’s just that Democrats here poll the way incumbents do nationwide.