Network News

X My Profile
View More Activity
Posted at 8:28 AM ET, 11/23/2010

The politics of cell phones

By E.J. Dionne

The Pew Research Center has performed an important piece of analysis that ought to shape the way we look at polls over the next two years. And its findings have real political impact, so please read on even if you're not obsessed with public opinion surveys.

There has been much debate in recent years over whether telephone surveys conducted only on landlines have produced distorted findings because so many Americans, particularly the young, now use only cell phones only. Pew has shown that this fear is justified. And it notes that this problem is growing. In essence, landline-only polls give the Republicans a measurable advantage.

Here's the key finding: "Across three Pew Research polls conducted in fall 2010 -- conducted among 5,216 likely voters, including 1,712 interviewed on cell phones -- the GOP held a lead that was on average 5.1 percentage points larger in the landline sample than in the combined landline and cell phone sample."

There's a reason for this. As Pew's report notes: "The difference in estimates produced by landline and dual frame samples is a consequence not only of the inclusion of the cell phone-only voters who are missed by landline surveys, but also of those with both landline and cell phones -- so called dual users -- who are reached by cell phone. Dual users reached on their cell phone differ demographically and attitudinally from those reached on their landline phone. They are younger, more likely to be black or Hispanic, less likely to be college graduates, less conservative and more Democratic in their vote preference than dual users reached by landline." (My emphasis added.)

Pew also found that the difference between samples that included cell phone users and those that did not had grown substantially since 2008, when "Barack Obama's lead over John McCain was on average 2.4 percentage points smaller in the landline samples than in the combined samples."

Okay, but the next election is almost two years away, so why does this matter now?

Between now and then, pollsters will conduct hundreds of surveys and their results will be averaged in together by many Web sites. These surveys will measure the popularity of President Obama, of Republicans and Democrats in Congress - and also public attitudes on many issues. We now know that surveys that poll only landline users will be skewed significantly in a conservative direction. And like it or not, surveys influence public opinion and (I know this is hard to believe) even the votes of some members of Congress on key issues. The public, for example, is split on the repeal of health-care reform. Landline-only surveys are likely to find artificially high percentages for repeal.

So here's a suggestion: All Web sites that report polling averages should confine themselves to samples that include both landline and cell-only users. If they include the landline-only surveys, they will be knowingly distorting their findings. If we are going to give so much attention to poll findings, we might as well be sure that the numbers are as close to right as we can get them.

By E.J. Dionne  | November 23, 2010; 8:28 AM ET
Categories:  Dionne  | Tags:  E.J. Dionne  
Save & Share:  Send E-mail   Facebook   Twitter   Digg   Yahoo Buzz   Del.icio.us   StumbleUpon   Technorati   Google Buzz   Previous: Opt out of the airport security hysteria
Next: Will Palin Power triumph?

Comments

Wow. I'll bet the weather was really nasty everywhere on November 2 as well. THAT explains the drubbing....

Posted by: scotpowell | November 23, 2010 8:41 AM | Report abuse

Polls are no different from anything else in our country. It's all for sale.

Payola is the name of the game and Republicans are paying. It's pay to play and pay to win.

Saudi Arabia owns much of Fox News. Where do you think their loyalties lie?

Posted by: getcentered | November 23, 2010 9:35 AM | Report abuse

I also think it is important to state clearly before you give the results of the poll, that the results do not reflect the knowledge of the interviewee about the subject matter. That is, just because a majority of people believe something, that does not make it true. I'll bet there was a majority of people who believed the earth was flat in 1490.

Posted by: mg11231 | November 23, 2010 9:49 AM | Report abuse

The masked premise here is that the media has credibility. The guy above who said it is for sale is dead on the money. After that they play with the numers till the number meet their needs. Cha Ching! ! !
In the instruction block "...other inappropriate comments..." can you say censor?

Posted by: jdiehl6 | November 23, 2010 10:40 AM | Report abuse

Them who control the press, control the people, how do you think Hitler got the people to follow him into the fires of hell, he was a master of controling the bulk of the population. and how he did it has not gone unnoticed.

Posted by: dv1236 | November 23, 2010 11:01 AM | Report abuse

@getcenterd: I agree with the first line of your post. The rest is the posting of a liberal democrat who is still stinging from Nov. 2nd.

BTW, what does Foxnews have to do with this article?

Wow, this site needs a way to properly reply to someone's post!

Posted by: TomDavisSr | November 23, 2010 11:18 AM | Report abuse

EXPERT SAYS OBAMA WILL NOT RUN IN 2012? IT IS BEING SPREAD LIKE WILD FIRE, REPUBLICANS WILL DEMAND OBAMA PROVIDE HIS LONG FORM BIRTH CERTIFICATE AS A CAMPAIGN PROMISE TO AMERICA. EXPERTS SAY OBAMA WILL FOLD HIS TENT UP AND NOT RUN RATHER THAN SHOWING HE IS NOT A U.S. CITIZEN...... WHAT YOUR TAKE ON THIS?

Posted by: Richie5 | November 23, 2010 11:36 AM | Report abuse

EXPERT SAYS OBAMA WILL NOT RUN IN 2012? IT IS BEING SPREAD LIKE WILD FIRE, REPUBLICANS WILL DEMAND OBAMA PROVIDE HIS LONG FORM BIRTH CERTIFICATE AS A CAMPAIGN PROMISE TO AMERICA. EXPERTS SAY OBAMA WILL FOLD HIS TENT UP AND NOT RUN RATHER THAN SHOWING HE IS NOT A U.S. CITIZEN...... WHAT YOUR TAKE ON THIS?

Posted by: Richie5 | November 23, 2010 11:36 AM


Shouldn't that state "Some experts ' just like faux noise does. This is the stupidest bit of rethugbagger nonsense I've heard yet.

Posted by: missgirl | November 23, 2010 12:37 PM | Report abuse

When you don't have either the facts or logic in your favor -- argue statistics. There was only one poll that mattered and it was conducted at the ballot box, not over the phone.

Posted by: johne37179 | November 23, 2010 12:38 PM | Report abuse

I guess only people with landlines voted? Funny stuff right there!

Posted by: FLvet | November 23, 2010 1:10 PM | Report abuse

"EXPERT SAYS OBAMA WILL NOT RUN IN 2012? IT IS BEING SPREAD LIKE WILD FIRE, REPUBLICANS WILL DEMAND OBAMA PROVIDE HIS LONG FORM BIRTH CERTIFICATE AS A CAMPAIGN PROMISE TO AMERICA. EXPERTS SAY OBAMA WILL FOLD HIS TENT UP AND NOT RUN RATHER THAN SHOWING HE IS NOT A U.S. CITIZEN...... WHAT YOUR TAKE ON THIS?

Posted by: Richie5 "

ANOTHER DELUDED GIBBERING IDIOT!

What's your take on THAT, Richie5??

Posted by: thrh | November 23, 2010 2:34 PM | Report abuse

two thoughts:

1) any statistician will tell you that a sample has to representative of the population (that would be landline or cellphone responders would be representative of election voters...). I would suggest that we are looking at *two* sub-population perspectives on the same event!

2) reading these comments is funnier than any/all the cartoons that I have read in months... do you people really believe the drivel that you are espousing? ...it is either really funny or really sad!

Posted by: JHLundin1 | November 23, 2010 3:31 PM | Report abuse

But don't reputable pollsters adjust the numbers to account for this? For example, if their poll has more Republicans than the national average, don't they readjust their numbers to take this into consideration? I'm a Democrat, but I'm not sure polls are as distorted as you claim.

Posted by: Dr_Bob | November 23, 2010 3:37 PM | Report abuse

Interesting theory, but one problem. If the polls give the Republicans a 5-point advantage, then the Democrats would have out-performed the polls on November 2 since the polls would have over-estimated Republican strength. But didn't happen. The Republicans won the races they were predicted to win and won the majority of the toss-up races.

And for all the morons who think that polls can be bought, please explain how the non-partisan polls such as Gallup routinely predict the actual outcome within the margin of error. The closer the poll is conducted to the election, the greater the accuracy of the poll when compared with the actual outcome.

Posted by: hisroc | November 23, 2010 3:52 PM | Report abuse

Evidently, people without landlines are not only younger, more liberal, less educated and less likely to be white.

They are also less likely to vote.

Posted by: pmendez | November 23, 2010 3:54 PM | Report abuse

Given E.J.'s logic, why don't democrats just make up their pole results.

Posted by: jbtaylor77 | November 23, 2010 3:58 PM | Report abuse

Given E.J.'s logic, why don't democrats just make up their pole results.

Posted by: jbtaylor77 | November 23, 2010 3:58 PM

*******************************************
They do. That's why they thought that ObamaCare would be popular when the real polls showed that 60% of the voters hated the bill.

Posted by: hisroc | November 23, 2010 5:58 PM | Report abuse

One other point about the last round of polls: my 23 year old son, a staunch Obama supporter, was so discouraged by the constant drone of "the Dems are going to get trounced" that he said "why bother to vote -- the republicans are going to win anyway." Of course I made him vote, but the total number of cell phone only twenty-somethings who were also discouraged from going to the polls is anyone's guess. It used to be (and still may be) that no polls were allowed to be made public in France during the last 2 weeks before an election. I think that's a smart rule.

Posted by: jpawlik1 | November 24, 2010 8:01 AM | Report abuse

"All Web sites that report polling averages should confine themselves to samples that include both landline and cell-only users."

Can't Dionne conclude a post without telling somebody what to do? Shouldn't it be sufficient to point out that polling that does not include both is flawed and should be viewed as such?

Posted by: West_Seattle | November 24, 2010 10:13 AM | Report abuse

One factor that nobody mentions is that all of the polls include only "likely voters", and do not represent the views of the entire population.

People who are AGAINST something are much more likely to take action, such as voting. Thus, polling tends to show more dissatisfaction with the party in power than actually exists. Herd mentality then draws in more undecided “likely voters” to oppose the current government.

It would be interesting to see the polling results for non-voters included in a poll. I wonder how close we are to a government of the people, by the people, and for the people?

Posted by: divtune | November 24, 2010 4:40 PM | Report abuse

Post a Comment

We encourage users to analyze, comment on and even challenge washingtonpost.com's articles, blogs, reviews and multimedia features.

User reviews and comments that include profanity or personal attacks or other inappropriate comments or material will be removed from the site. Additionally, entries that are unsigned or contain "signatures" by someone other than the actual author will be removed. Finally, we will take steps to block users who violate any of our posting standards, terms of use or privacy policies or any other policies governing this site. Please review the full rules governing commentaries and discussions.




characters remaining

 
 
RSS Feed
Subscribe to The Post

© 2010 The Washington Post Company