During the last half of 2009 approximately one quarter of US households used mobile phones instead of landlines, according to a study by the National Center for Health Statistics.
The trend towards household mobile has been going on for years. Take, for example, a survey size of me: I haven’t had a home landline in ten years or so.
Need a larger sample size? Here’s what the NHIS has to say:
The percentage of adults living in wireless-only households has also been increasing steadily [see Figure below]. During the last 6 months of 2009, more than two of every nine adults lived in wireless-only households. One year before that (i.e., during the last 6 months of 2008), 2 of every 11 adults lived in wireless-only households. And 2 years before that (i.e., during the last 6 months of 2006), only 2 of every 17 adults lived in wireless-only households.
The percentage of children living in wireless-only households is also growing. In fact, for this population, the 4.6-percentage-point increase from the first 6 months of 2009 is the largest 6-month increase observed since 2003, when NHIS began collecting data on children living in wireless-only households.
And for the visually inclined, the NHIS provides the following handy timeline:
Other eye-catching statistics from the research shows that 49% of adults aged 25-29 live in a mobile-only home, while 30% of all US Hispanics are cellphone only.
While the landline to mobile trend will continuously affect how we communicate, receive and share information, more interesting — and more profound — is an analysis by the Pew Research Center.
It seems that pollsters and other surveyors of national life generally rely on the traditional telephone to conduct their research. It’s simply much less expensive to do so. As Pew points out, with large numbers of US household now off the landline grid, “non-coverage bias” creeps into polls of all sorts.
For some estimates, even a small amount of bias may have important substantive consequences for the political or social implications of the research. Since the decline of landline coverage has not been uniform across demographic groups, non-coverage bias among certain subgroups may be even larger than for the full sample. As a result, some key subgroups in surveys based only on landlines may be severely underrepresented.
Since we’re in an election year, let’s look at two political polls and how they effect news coverage.
- In polls of landline users only, Republicans lead generic horse races. Once cellular-only adults are included, these races become dead heats.
- When sampling both cellular and landline users, more people approve of President Obama’s performance than disapprove. Limit the poll to landline users and equal numbers approve and disapprove.
Polls drive political coverage and in general most polls referenced by major media exclude the mobile-only population. Pew shows that such exclusion has a significant effect on overall results which in turn shapes the news narratives we see bandied about as accepted wisdom.
With the mobile-only trend growing, it appears that “reality-based” coverage of our civic and political life will grow more skewed with large segments of the population unaccounted for.
How to prevent that? It’s a matter of dollars and cents. Money that pollsters are well advised to spend.
