Articles and Analysis


NJ Watch (Friday) Plus an Automated vs. Live Interviewer Bonus

Topics: Automated polls , Chris Christie , Chris Daggett , independents , Jon Corzine , New Jersey 2009

The most recent polling in New Jersey shows an excruciatingly close race between incumbent Democrat Jon Corzine and Republican challenger Chris Christie. As of this writing, our standard trend estimate (below) puts Corzine "ahead" by a negligible 0.8% (41.4% to 40.6%). The more sensitive setting on our smoothing tool makes the Corzine margin slightly narrower (0.6%), the less sensitive setting makes it slightly larger (0.9%). Any way you look at it though, the differences between the estimates -- and more importantly, between Corzine and Christie -- are virtually meaningless.  Right now, the current polling snapshot of this race is a close as these things get.

For perspective on the closeness of the margin you might want to stroll down memory lane and revisit my final Election Day update from Tuesday, November 4, 2008. We showed only four states where the Obama-McCain margin on our trend-estimates was less than 2 percentage points, and the leader ultimately won the state in 2 of 4 states. So a margin of under two percentage points puts us well within true toss-up territory in terms of predictive accuracy, especially with a weekend of polling still to go.

Understandably, the close nature of the race has political junkies turning these numbers upside down and reading every possible tea leaf and in search of the key to the outcome. After doing much of the same (while out with the flu) the last few days, the best answer I can give based on the empirical evidence -- for the moment at least -- is that this race is currently looking very close.

Are things trending toward Corzine? Yes, when compared to early September, our chart indicates a decline of roughly four percentage points for Christie and an increase of roughly three points for Corzine. Over the course of the summer, Christie had been dropping (from a high of roughly 49% in early July), while Corzine remained flat.

What is less clear is whether the closing trend has continued over the last two weeks. As of this writing, only three pollsters have tracked more than once since mid-October, allowing apples-to-apples trend comparisons. Two, SurveyUSA and Democracy Corps -- show Corzine's margin two percentage points better. One, Rasmussen, shows it one point worse. None of these differences are statistically significant alone and the patterns are obviously small and inconsistent.

That said, the trend over the next four days may not be as smooth, and the Daggett "wild card" that everyone has focused on for the last few months is the reason. Consider at least three ways that the Daggett effect leaves us even more uncertain about the outcome:

Individual level uncertainty -- The Monmouth University Polling Institute reported yesterday on a focus group they convened earlier this week in Edison, NJ among voters who are still either undecided or just leaning to a candidate. While they explicitly warn against treating the findings as representative of all undecided voters, the most clear finding was a sense of unhappiness with both major candidates: "These voters claim that this is the most difficult election choice they have ever faced. Nearly all said that Jon Corzine has not done a good enough job to deserve reelection. They simply have not heard enough from Chris Christie to cast their lot with him." Their final decision about Daggett, the report says, may come down to whether he has a chance of winning.

Aggregate level uncertainty -- One statistic worth pondering: On the last ten polls, all conducted in the last week, the portion of the electorate that is either undecided or supporting a candidate other than Corzine or Christie averages 16.5% (with a range of 11% to 23%). As a crude measure of voter uncertainty, that's considerably more than 5% or so we saw at this stage of last year's presidential election.

Measurement artifacts? -- Complicating this issue even further are the measurement challenges that pollsters face when testing lesser known independent candidates, especially when voters are unhappy with the top two choices. Offer just three choices and no explicit undecided category and some undecided voters will choose the independent as their way of expressing uncertainty. On the other hand, fail to prompt for the independent and you may measure a number that's much lower (see, for example, the intriguing experiment embedded in the Fairleigh Dickinson poll). Reality likely falls somewhere in between. And no one can be certain of the effect that the other 9 candidates will have.

And finally, there is the intriguing pattern noted earlier this week by PPP's Tom Jensen and explored last night by Nate Silver. Christie has done consistently better on telephone polls conducted using an automated, recorded voice than on those using live interviewers. Using the filter tool on our chart, as of this writing, Christie runs roughly three points ahead of Corzine on the automated polls, but Corzine runs a little less than three points ahead on live interviewer polls. The chart below, which Charles Franklin kindly prepared this afternoon, shows that the difference has been consistent throughout the race (his margins are likely different than on our interactive chart due to his use of slightly different smoothing levels).


We also see a similar though far less pronounced and consistent effect in Virginia, and then only since Labor Day.


What this effect is about, and what it portends for the outcome in New Jersey, I cannot say. Nate Silver has some plausible speculation about automated surveys being potentially more sensitive to an enthusiasm gap between Republicans and Democrats, although if that is true, I have no explanation for why we saw no such consistent difference between automated and live interviewer surveys in the Obama-McCain polling last year. We should have new surveys over the weekend or on Monday from all three automated pollsters in New Jersey (SurveyUSA, PPP and Rasmussen) and from at least three of the live-interviewer polls. So this phenomenon will be interesting to watch.

Either way, the combination of a very close snapshot and many indicators of potential volatility makes for a very uncertain outcome.




I can give you the simpliest explaination of all why there is a difference between an IVR poll and a live interview poll, and I am virtually certain that Silver won't want to hear it.

When you do a live interview, you are telling someone how to vote and that means that someone else can (potentially) get that information and use it against you (strongarm tactics). With an IVR, you can poll anonymously.

I note that there is a reason we use a secret ballot in this country.

Given that, and given there is a difference this year, I'd go with the IVR results all other things being equal.




Polaris is making a case for a "pseudo" Bradley effect in his commentary regarding the difference between IVR and Live interviews. I would take the opposite view in this election. In an impersonal, automated survey, voters could take out their frustration with Jon Corzine and "hit the button" for Christie. But when a live individual asks the question, they give the true answer, that, albeit reluctantly, they'll vote again for Corzine. In NJ, history says that voters always tell people they're voting Republican and then vote Democratic. If they're actually telling a live individual that they'll vote Democratic, then Corzine will probably win by 6-8 points, not 3.



I really don't know who will win in New Jersey. I am certainly for Corzine but the polls indicate that the race is extremely tight.
I notice however that Polaris, previously better known as the so called expert on polling at the Hedgehog Report, bases his opinions, not on fact but by who does the poll. If it shows the Democrat will win, that poll is biased. Last year, he kept saying that ALL of the polls were biased and that McCain would win.
No one knows who will win in NJ. That is the conclusion of anyone who believes in objective data, which conservatives do not.




I also admitted where I made my mistakes. Funny but that's something not a lot of people do.

I also notice that you attack me the person rather than the argument I am trying to make.

I am not saying that any poll with a Dem is automatically biased. I am not saying that Corzine can't win either.

All I have said here is that given that we have a secret ballot and given New Jersey's unfortunate history with voter intimidation and fraud, it seems reasonable to assume that the IVR poll is more accurate.


This ability to take out one's frustration in private is one big reason I think ultimately Corzine will lose. If a voter can do that in private with a pollster, history suggests he will certainly do so at the ballot box. This is true for both parties.




One last comment about last year since Alan Snipes has decided to make me the issue (and shame on him for doing so).

Yes I did think all the polls were biased and given the information I had then, I stand by what I said. My reasoning was very simple if you bothered to read what I posted on HH instead of reacting. I regard Self-Partisan ID to be generally static. I regarded it (and usually still regard) it so based on nearly thirty years of national elections! Thus I thought that all the polls at the time were making the same mistake. If 20 pollsters make the same mistake, they all will be wrong. That was my point then and given what I knew then, I stand by it.

2008 was an anomaly. In 2008 the self-identified partisanship really did change in a way not seen for decades....but then again the entire race was being held in the middle of an economic collapse. A closer look at the exit poll demographics reveals that millions of people that should have been expected to vote (and were expected to vote by both parties) did not.

The percentage of new voters was about 12% but the increase in VEP in 2008 (from 2004) was only 4% (a bit less actually). Both parties in 2008 were expecting nearly 140million voters based on enthusiasm (which would have been consistant with a 12% VEP increase). In fact the total number of voters was only about 130 million.

I also note that 2008 had IMHO some of the worst polling in record. Sure I was badly off and I admitted it then on HH and admit it here and now. However, the big media polls as well as Gallup using their expanded models were also badly, badly off....and I saw very little sign that anyone other than a few pollsters actually had any feel for the race.

BTW, one of those that did was Scott Rasmussen and he uses an IPV technique. Given that Rasmussen has been right for the last three election cycles (2004,2006 and 2008) you might want to give some credence to what he's saying now about NJ especially when PPP (who was also nearly dead on in 2008) is saying the same thing.



Rasmus Pianowski:


I don't know where you get the idea that Rasmussen was 'dead on'. He hit the national popular vote, sure. But you know very well that this is luck. There's a margin of error on every poll and even if Rasmussen were perfect and made only correct assumptions on turnout AND could reach every potential voter he couldn't expect to reliably nail the race.

A pollster who missed the final result by 2 points isn't necessarily worse than someone who missed it by .02, just less lucky.

But if you luck at the statewide results, where the sampling size (and I mean of number of polls) you can look at is bigger, Rasmussen didn't do so well.

Obama by 4 in Colorado? McCain wins Florida? Obama by 4 in Pennsylvania? McCain by just 8 in Mississippi? Didn't turn out that way...




I believe he (Ras) pretty much got NJ though. However, that is bye the bye. My only point here is that given there seems to be a non-trivial difference between IPV and live-interview polls unlike other times (including 2008 which did have a high Dem enthuiasm factor which seems to counter Silver's thesis), and given that in New Jersey because of it's sordid political history, voters have a strong incentive to lie to a live interviewer (for what should be obvious reasons), it is logical to conclude that the IPV polls are better indicators all other factors being equal.

That was all I wanted to say in the beginning and all I wish to say now. In short I think Nate Silver and Mark here are making a real effect a lot more complicated than it is. In New Jersey, there is a strong incentive to LIE to a person doing a live interview and the polls reflect it.



Some points you make, Polaris, may be true. However, it's clear you know very little about NJ politics and polling. In every election I can remember, the Democratic candidate far outperformed his or her polling data on a statewide basis. New Jerseyans are basically New Yorkers and Philadelphians and if you ever went to sporting events in those two cities you know how cantakerous the population is. They'll tell live people "the sky is green," because they want to confuse the live person, but will probably hit the "sky is some other color" button on a computer, because they don't care about the computer.

No poll in my recollection had Obama winning NJ last year by 17 points. No poll had Lautenberg winning with ease earlier and in 2004 a lot of polls had Bush beating Kerry in NJ. Guess what -- the Democrat always way outpolls the polls in that state.




We'll see in just a few days and I won't belabour the points I've already made. Suffice it to say that angry voters tend to vote out unpopular incumbants.....even in New Jersey.



Post a comment

Please be patient while your comment posts - sometimes it takes a minute or two. To check your comment, please wait 60 seconds and click your browser's refresh button. Note that comments with three or more hyperlinks will be held for approval.