iPhone app iPad app Android phone app Android tablet app More

Pre-election Poll Methodology: What the Public Has a Right to Know


The following piece is part of an ongoing series of OffTheBus reports by citizen policy experts critiquing different aspects of Campaign 08. The author is president of the American Association for Public Opinion Research (AAAPOR).

The buzz over the recent Zogby online poll that finds Senator Hillary Clinton losing to all four top Republicans in head-to-head trial heats reinforces the public's right to know and understand and the media's obligation to report the nuances of survey and polling methodology.

But what exactly should we be asking when we look at these poll results? Both the American Association for Public Opinion Research (AAPOR) and the National Council on Public Polls (NCPP) offer a list of questions for journalists to ask when reporting on polls. Consumers of election polls should be asking the same questions. One question is particularly relevant to the current debate: What population is (who are the people) represented by the poll?

In the case of an online panel survey (like Zogby's) only those individuals who have previously joined the panel have an opportunity to be surveyed. As noted in their methodology, "Zogby has assembled a database of individuals who have registered to take part in online polls through solicitations on the company's Web site, as well as other Web sites that span the political spectrum." From this pre-registered group, a random sample is selected. So what's the population that is actually represented by the poll that was recently reported by Reuters and others? The answer: those individuals who have identified themselves previously and registered to be part of the panel.

We know from the past (the 1936 Literary Digest presidential poll being the most famous) that even samples that are selected at random can be hopelessly flawed if respondents are selected from a source that does not represent the population of interest. (See here on random sampling and here for more information about sampling and why it works).

Telephone surveys are not immune to this problem (albeit for a different reason). Most telephone surveys only include land-based telephone lines, although a growing body of research has been investigating the impact of including or excluding cell phone numbers as part of the sample. Here too we can ask the question "what population is represented?" If only land-based telephone lines are included in a telephone poll, then the answer to the question is those individuals who live in residences that include a land-based telephone line. As the cell-phone-only population grows this becomes an increasingly important question to ask.

There is no one right way or wrong way to conduct pre-election polls. What all of us need to be mindful of during the primary season is that polls vary in quality--and without the disclosure of detailed methodology about the survey neither journalists nor consumers have the ability to evaluate them. Zogby in their press release does indicate that the poll of interest was an online poll--what was lost in the hype was the disclosure of that information as part of the reporting of the poll. AAPOR advocates disclosure of methodological details for all surveys and polls that are part of the public domain, and the association strongly supports the Disclosure Project of Pollster.com, an independent source that has explicitly taken on the task of soliciting this information from all pollsters and making them easily available. The Internet has rendered moot the excuse that methodological details cannot be provided due to limited space and airtime.

Disclosure Note: Mark Blumenthal, aka Pollster.com is a member of the AAPOR Executive Council

 
 
  • Comments
  • 28
  • Pending Comments
  • 0
  • View FAQ
Comments are closed for this entry
View All
Favorites
Recency  | 
Popularity
Page: 1 2  Next ›  Last »  (2 total)
HUFFPOST SUPER USER
wrabbitt
Soylent Green IS People.
04:44 PM on 12/07/2007
POLL THIS! We all hear about polls and some people actually believe the results, + or- .03% error. I don't need to be polled i ain't going to tell you the truth even if you ask. its my business. Poll how many people believe that the government is run by bribes from lobbyists, Or how many people Love america,and hate the government, or how many people donate to their favorite candidate and believe their 50$ is going to sway their vote as much as the 1 million from big drug/insurance. The totals will scare you . but they will never come to light.
04:17 PM on 12/07/2007
IF THIS NEXT PRESIDENTIAL ELECTION IS AS CLOSE AS BUSH'S TWO.......I BELIEVE THAT INSTEAD OF WALKING AWAY A "RECOUNT" SHOULD BE DONE...AND NOT GIVE THE ELECTION VIA THE FLORIDA COURTS TO THE SUPPOSID WINNER....BUSH CLAIMED HE HAD A "MANDATE"......HE HAD A LUCKY STREAK W INCOMPLETE COUNTING!!
06:22 PM on 11/30/2007
Turd Blossom is alive and working very hard!

The media is doing it's masters bidding!
05:19 PM on 11/30/2007
Kucinich is the best Progressive choice, Edwards is second.
Ron Paul has integrity and his concern about restoring the Constitution is right on.
If only he were truly for Freedom and wasn't a forced birther .
Also the Free market does not exist . Do you really think that the Big Money , fossil fuel interests will allow alternative energy unless they can control it? They have already stopped the importation of the Smart car ( they now support it because they control it) and GMs famous electric car saga is another example.
Big Money hold all the cards in influencing government and use regulation to their advantage.
Stopping the big brother, Soviet Style of government that has grown into a monster under Bush is the #1 problem to deal with.
Without Freedom America is nothing...bush and the neoCONs , republicans and many Dems have helped make the USA a Soviet Style of government.
photo
HUFFPOST SUPER USER
Tulka2
Solidarity. Courage. Humor.
05:02 PM on 11/30/2007
This is the most important question to ask any Democrat: "If you 'lose' on election day, will you demand a careful, public re-count? Or will you quietly fold your tent and walk away ala Gore and Kerry? Will you fight for our vote?"
02:59 PM on 11/30/2007
Perhaps candidate preference polls should be banned entirely except perhaps for internal use of a campaign to evaluate strategy. I agree with the Orwell remark---we need to be very wary of the constant reporting of polls---whetheror not it is a deliberate attempt to limit or sway public thinking. It is so superficial. Can't at least in the selecting of our chief executive, we try for a level playing field? Yeah yeah, I know! Not a chance, but it is nice to dream. Then we could start demanding a real discussion of issues. Our eklectoral process as it stands is a scandal.
10:56 AM on 11/30/2007
I don't remember this level of fixation on the pre-election polling data before the era of karl rove politics. Whether intended or not (and I believe it is), this allows the media to have and unfair influence over the outcome of the election.

I'm sure that by now, everyone here is familiar with George Orwell's prophetic book - "1984". He did write other books, and in fact I had to do a book report on one of them in high school. The book is called "Animal Farm", and it can be read online at Google Books. I didn't really understand it at the time, but it is an equally prophetic book, and is well worth re-reading.

In the book, Orwell introduces one of his other famous words: "groupthink". Despite Orwell's warnings about the dangers of it, in this country, we have embraced it; although we give it a more marketable and PC name: "conventional wisdom".

Through their constant hyping of the polling data, they are able to maintain the "conventional wisdom" that HRC will win the democratic nomination, for example. Of course, when they started pushing these polls over a year ago, most people didn't even know who else was running besides Hillary, so of course these early polls favored her. In this way, they are able to take a result that is favorable to them, and through repetition and message-discipline, they are able to turn it into a self-fulfilling prophecy.
09:05 AM on 11/30/2007
Polling methodology is inconsistant with the world we move in today. There is no appropriate place to take a poll because they take too long and Americans can not sit still long enough to respond to the questions needed to complete the poll. Land line polling is a joke as the American public is either screening calls or waiting to talk to anyone who calls, both groups are suspect.

The questions asked on polls should be suspect too. Consider Hilary Clinton's recent statement that she will dedicate $50 billion to aids research if elected. Can that even be considered as there is no way she
will get the support to spend that kind of money from congress. It seems we should be looking deep into the candidates back grounds and making voting decisions based on what they've achieved rather than what they would like to achieve or what the people who have time to respond to all the questions beleave they mean when the campaign spin goes to press.
08:50 AM on 11/30/2007
there is always a poll out there that will back what you believe it seems.

I think random nationwide phone polls are the most reliable only inso much that it is random and not a reliable number that read of subscribe to media or polls like zogby.

PollingReport is decent to scan only because it lists numerous polls , right and left based , and from there you can get a clue , but not much else.

Remember however the majority of people don't participate in polls at all.
08:05 AM on 11/30/2007
I'm pretty sure that after breathlessly announcing the latest results of a New Hampshire poll, the news anchor said, "Keep in mind that 74% of voters have not yet made up their minds."
HUFFPOST SUPER USER
ljsfolly
07:26 AM on 11/30/2007
The problem as I see it is that too many people believe the polls and take them so seriously that they will go to vote with the latest poll they remember. They are thinking they have to vote for the winner as what would they tell annyone who asked after the votes were in? I voted but I voted for the other guy? When Bush was still perceived to be the "best" and "saving us from terrorists" so many epople voted for him it should have been a landslide but we know it wasn't. When he showed his true colors the amount of people who voted for him were the ones still with a "W" on their car/truck. The polls are all the same way and cannot trust them either for the truth.
06:44 AM on 11/30/2007
While I, a life long Republican, could never vote for Hillary Clinton unless she were running against George W. Bush, the current president, I have always been concerned about the procedures involved in poll taking, and the effects upon the election. Many people have a knee jerk reaction to the results, and immediately jump on another candidate's bandwagon if they feel that their initial choice is not electable.

I also am gravely concerned about the media power brokers who have made their choices about WHO are the "top tier" candidates of both parties, and upon what basis this has been done.

As a Republican who happens to be Caucasian, I can certainly tell you that Obama makes a lot of sense to me, and I could easily vote for him because I am so disgusted with the top tier Republican candidates; they only promise more of the same, and to my mind, it's not good enough. My only concern is that the rumor that he's a protege of Sen. Lieberman might be true. Also, as I look at Ron Paul I see "images" of Abraham Lincoln, and I "wonder" why the Media Moguls are down on him.
photo
janmB
loves life
06:11 AM on 11/30/2007
I have never been in a POLL nor do I even know anyone who has. Now just like ENRON --just like our gov't when figuring COLA the books can be cooked and displayed any way you want them to look.
01:40 AM on 11/30/2007
I just want to point out that the subset of people with landlines isn't just that, it is of people with landlines, who are home - and who answer polls.
No one I know will answer a person calling them for polls for many reasons; it is invasive, it takes too much time, and it seems to result in getting more phone calls.
I wonder if there is a difference between the people who will answer polls and those who say "no thanks". I'm curious what the rate is of people who refuse to answer questions.
I also wonder if that rate has gone up since the do not call list started.
HUFFPOST COMMUNITY MODERATOR
Pdubya
12:23 AM on 11/30/2007
All of the "national polls" are useless. The MSM are paid shills of the Council on Foreign Relations, of which, most of the blue and red plutocracy are members.

I do know this, however:

http://www.infiniteronpaul.com/meetupmaps/

thanks for the piece, nancy!