That NH primary poll
Perhaps you’ve seen it. You know, the one that shows Trump way ahead of the rest of the Republican field at 40%?
The poll is somewhat odd, however. For example, the number of Republican voters in it is 472, not a very big number. I know New Hampshire’s a small state—but still, that’s pretty tiny, as polls go. It means that Trump’s 40% is a grand total of 188 people, while Carson’s 12% is 56 and Fiorina’s 8% is 37. The announced margin of error is large, plus or minus 5.1% (the smaller the sample in a poll, the more likely that the results are inaccurate, although other factors come into play as well in determining accuracy).
Another possible problem is that, of poll respondents who say they are likely to vote in the Republican primary (question 19), only about a third describe themselves as “strong Republicans,” a third as “lean Republican,” a fifth as “not very strong Republican,” and a smattering as “not sure.” Is this actually a representative group of Republican primary voters? It doesn’t quite sound that way to me, but I don’t know. Who are these people?
Let me just add that one of the reasons I’m wondering about all of this is that I remember that in 2008 the polls were way off in predicting the New Hampshire primary results, and I’m talking about polls taken very close to the primaries themselves, not far away like the one the other day:
One of the biggest stories of the NH primary is the failure of the polls to have accurately predicted the results. It’s not that it’s so unusual for polls to be incorrect, but for so many to be incorrect in exactly the same way””predicting about an 8% Obama victory and getting a result of Clinton by 3%, off by a factor of approximately 11%””is highly unusual.
In that post of mine, by the way, I stated that, in my group of liberal female friends, Hillary was not favored over Obama, and I predicted that she’s run into trouble despite her NH win.
The reason I remember that poll/primary disconnect back in January of 2008 is because the NH polls had been so massively wrong:
On Monday and Tuesday, seven independent polls showed Obama ahead by an average of 8.3 percentage points, according to the RealClearPolitics website. When the votes were counted, Clinton won by 2.6 percent.
What happened? The pollsters have theories, but no one is sure.
“It was a total shock,” said Scott W. Rasmussen of the independent Rasmussen Reports, whose final three-day tracking poll – a total of 1,200 likely voters through primary eve – showed Obama ahead by seven points, down from 10 the day before.
“I can’t remember a time when the entire polling industry showed a similar result and it was wrong,” he said.
That’s pretty dramatic. The rest of the article tries to explain, but in my opinion it fails. But here’s a possible clue, though:
While the wayward polling this season is dramatic, it happens with regularity in New Hampshire, where voters aren’t shy about expressing their contrariness – electing dark horses or upstarts, and smacking pollsters upside the head…
“Do Granite State voters enjoy fooling pollsters that much?” Nolan [Globe columnist in 1984) asked. “Is massive mendacity part of the local color?”
Food for thought.
[ADDENDUM: By the way, for all you Trump supporters out there, I’m not questioning the fact that Trump is the frontrunner. I believe that he is. I’m questioning the accuracy and meaning of this particular poll saying he’s at 40% in New Hampshire. I’m also questioning state polls in general, particularly with rather small samples and a very large field of candidates.]
I live in NH when we had a landline we got calls ad nauseaum, I did *toy* with them giving results, I believe Dems with their agenda were frequent callers trying to gauge where the *wind was blowing*.
Once I responded to the question “Who will you be supporting in the upcoming NH primary?”
I said Obama (LOL) the polltakers response always stuck with me he responded “Good”. It surprised me that a poll taker would editorialize that way, so I guess that made me think it was an *inside poll* & not one of the legitimate polls.
Yes & you are right about NH voters they throughly enjoy thumbing their noses at experts, for how long that will be the case ??? I don t know as now thousands of out of state college students are voting in NH, & unfairly stealing the residents vote since they cast ballots on state offices & referendum issues where they have no actual interest in the issues. Very disheartening for us residents.
About Polls:
1. The “margin of error” announced with polls is not a red herring. It is a flaming crimson sperm whale. It is a formulaic mathematical calculation that works just great if you want to approximate the average weight of apples in an orchard, assuming your scale is not a truck scale that is accurate to the nearest hundred pounds. It is totally erroneous if you are measuring opinions – the data are fuzzy.
2. The sample is not representative:
“At Pew Research, the response rate of a typical telephone survey was 36% in 1997 and is just 9% today.”
http://www.people-press.org/2012/05/15/assessing-the-representativeness-of-public-opinion-surveys/
There are obviously a number of factors influencing the response rate. They’re just not sure what they are.
Henry Ford once said, “I know only half of my advertising works. The problem is, I don’t know which half.”
The non-representative problem caused the first great polling goof – “Dewey Wins”. It was a telephone survey at a time when telephones were not in every household.
3. Polling firms are businesses whose income comes primarily from marketing research. They compete with each other based on accuracy. Public opinion surveys, where it is impossible to measure accuracy, are publicity. They are often used as training vehicles for junior employees.
4,5,6,7 …
You’re bored with this. So am I.
@ Roy “It is a flaming crimson sperm whale.” Great line.
I am a NH voter and we just don’t answer our landline much now thatWe used to go through with it at least occasionally. The theory behind having NH as first-in-the-nation (nod to Iowa and SC) doesn’t apply so well anymore. It used to be an opportunity for a candidate with less money and name recognition to get his foot in the door. That’s no longer the case. By the time we vote in Feb 2016, anyone who wants to stay in the race has to have lots in the account by then. And then will need even more. The national coverage overwhelms what happens here now.
And I’m sick of it. When my children were young it was fun to take them to events and meet candidates and having something real and concrete to discuss with them. Those days are gone.
My take from the folks I work with is that Trump is attracting people who don’t usually vote, who are mostly concerned that illegal immigrants “get stuff” while hardworking citizens are struggling, who believe “neither party has been doing anything about it,” and who follow the strong horse. He owns that group. People who have better-informed versions of those complaints aren’t quite as sold, but they far prefer him over the other SOB’s.
So even if they aren’t really conservatives, they have some elements – and they just might show up to vote.
Hi AVI,
I check in with your blog every day. I don’t comment much because I find very little with which to disagree.
My suspicion is that many Trump supporters, particularly the vocal ones, are the Ron Paul army of yesteryear. Why not Rand? Not loopy enough.
The primary/convention system is revival theater, the 32nd quadrennial community players performance of A Glass Menagerie. I’ve been watching the show since 1952. The most interesting parts are the flubbed lines, missed marks and a vast audience of clueless critics. Comforting in a way.
Regards,
Roy
p.s., when is that promotion coming through?
“The poll is somewhat odd, however. For example, the number of Republican voters in it is 472, not a very big number. I know New Hampshire’s a small state–but still, that’s pretty tiny, as polls go.”
Whistling through the graveyard.