New results the Pew Research Center for the People and the Press have confirmed what many people and some pollsters have long suspected. Polls that survey only land line users are biased towards Republican Party. The survey found that excluding cell phone users inflates the GOP edge by 4-6 points.
Although 25% of US households no longer have a land line, the vast majority of pollsters still survey only land line households. According to the Pew study, “In three of four election polls conducted since the spring of this year, estimates from the land line samples alone produced slightly more support for Republican candidates and less support for Democratic candidates, resulting in differences of four to six points in the margin. One poll showed no difference between the land line and combined samples.”
Pew found that Democrats gained four points in their most recent poll among all voters when cell phone users were polled. Among likely voters in the same poll, Republicans gained an additional five points when land line line users made up the entire sample. The reason for this disparity is that younger people tend to have ditched their landlines, and rely solely on their cell phones. Older voters are more likely to still have a land line. Older voters are also the backbone of the Republican Party.
This isn’t an intentional bias by pollsters. Cell phone numbers are private. There is no phone book for cell phone users. This has put pollsters, especially automated pollsters, in a real bind. Their decades old methodology for gathering data has not kept up with technology. Most cell only users tend to be younger, and they are also more likely to support the Democratic Party, which means that they are going to be under represented when traditional polling methodologies are used.
Any organization that does all their polling via a telephone automated system is especially susceptible to falling victim to the phone preference bias. Pollsters have so far been unable to find reliable way to obtain a more representative sample for their polling. Some polls like the NBC News/Wall Street Journal poll do include cell phone users, but the vast majority of polls don’t. This is just another variable to keep in mind, when you read, or hear about a poll. All polls are not created equally, and poll results that don’t include cell phone only households are almost certain to have a Republican bias.