With Cell Phones Excluded From Surveys, Are Polls Skewed?

Today's Best Tech Deals

Picked by PCWorld's Editors

Top Deals On Great Products

Picked by Techconnect's Editors

Sen. Harry Reid is questioning the validity of polls showing him in a close race with Republican challenger Sharron Angle for his U.S. Senate seat in Nevada because random phone surveys fail to include calls to cell phones.

With cell phone users not being polled, the results are skewed in favor of home phone users and not the broadest audience, Reid said in a CNBC interview (see video, below), which was posted on The New York Times' Web site on Friday Oct. 22.

Cell phone users, who tend to be a younger and more transient group according to various surveys and carriers, are probable supporters, Reid said in the interview. They largely comprise a group that Democrats like Reid have traditionally counted on for support.

A week earlier, on Oct. 13, the Pew Research Center issued a statement saying that nearly all election surveys rely on wired, or landline, phones and, therefore, could be biased.

"Virtually all" automated polls don't include interviews with people on cell phones, Pew said. And Pew noted that National Center for Health Statistics data says the one-quarter of all U.S. households have only a cell phone.

Reid implied in the video that his own internal polling includes cell phone users and that those survey results show he's doing OK in the race with Angle. He didn't elaborate, and his campaign could not be reached for further comment.

"I feel comfortable with where I am [in the race] and what I've done," Sen. Reid said in the CNBC interview. "We do our own polling and they are scientific polls, not like the ones that are floated around in the newspapers."

"I'm not making this up: These polls [in the newspapers are] done by random dialing. They can't dial anyone with a cell phone," Sen. Reid said.

Despite wide pronouncements by Democrats that Angle has extreme conservative views, several polls have shown her besting Reid by a point or two.

One widely respected pollster, Rasmussen Reports, gave Angle the edge over Reid by 50% to 47% in its most recent telephone survey of 750 likely voters in Nevada, released on Oct. 18.

In seven prior Rasmussen polls, the two candidates were consistently three points apart or less.

Scott Rasmussen, president of the independent polling firm, said by e-mail that Rasmussen Reports surveys do not incorporate cell phones, although the company is experimenting with ways to do so in the future.

However, Rasmussen argues that including cell phone users would make little difference in the survey results for 2010.

He noted that young adults both with and without landline phones "tend to be more supportive of Democrats than their elders." Be he said, "At the same time, they are less likely to show up and vote this year."

Young voters also typically turn out in greater numbers for presidential elections than mid-term elections.

The impact of cell phone users on surveys "is likely to change within the next couple of years," which is why Rasmussen Reports hopes to reach cell phone-only users in future years, he said.

Artwork: Chip Taylor
Pew's analysis is different. It noted that landline survey samples (compared with landline along with cell phone samples) in three of four polls conducted since the spring of 2010 produced "slightly more support for Republican candidates and less support for Democratic candidates, resulting in differences of four to six points in the margin." The fourth poll showed no difference.

A fifth Pew poll of 2,816 likely voters conducted in late August and early September included 786 reached by cell phone. It showed 43% would vote Democratic in congressional races and 50% would vote Republican. Excluding the cell phone likely voters, the landline results went for Republicans by 53% to 41% for Democrats.

Pew is planning a more comprehensive analysis following the Nov. 2 elections.

Angle's spokesman could not be reached to comment on this issue.

Matt Hamblen covers mobile and wireless, smartphones and other handhelds, and wireless networking for Computerworld. Follow Matt on Twitter at @matthamblen or subscribe to Matt's RSS feed. His e-mail address is mhamblen@computerworld.com.

This story, "With Cell Phones Excluded From Surveys, Are Polls Skewed?" was originally published by Computerworld.

Note: When you purchase something after clicking links in our articles, we may earn a small commission. Read our affiliate link policy for more details.
Shop Tech Products at Amazon