January 31, 2008

The Impact Of “Cell-Onlys” On Public Opinion Polling

Ways of Coping with a Growing Population Segment

About the Survey

The findings in this report are based on two telephone surveys conducted under the direction of Princeton Survey Research Associates International (PSRAI). The first was among a nationwide sample of 2,007 adults, 18 years of age or older, from October 17-23, 2007 (1,507 respondents were interviewed on a landline telephone, and 500 were interviewed on a cell phone, including 199 who had no landline telephone). The second survey was conducted among a nationwide sample of 1,430 adults, 18 years of age or older, from December 19-30, 2007 (1,089 respondents were interviewed on a landline telephone, and 341 were interviewed on a cell phone, including 113 who had no landline telephone).

A combination of landline and cellular random digit dial (RDD) samples was used to represent all adults in the continental United States who have access to either a landline or cellular telephone. Both samples were provided by Survey Sampling International, LLC (SSI) according to PSRAI specifications.

Numbers for the landline sample were drawn with equal probabilities from active blocks (area code + exchange + two-digit block number) that contained three or more residential directory listings. The cellular sample was not list-assisted, but was drawn through a systematic sampling from 1000-blocks dedicated to cellular service according to the Telcordia database.

For the landline sample, interviewers asked to speak with the youngest adult male currently at home. If no male was available, interviewers asked to speak with the youngest female at home. This systematic respondent selection technique has been shown to produce samples that closely mirror the population in terms of age and gender. For the cellular sample, interviews were conducted with the person who answered the phone. Interviewers verified that the person was an adult and in a safe place before administering the survey. Cellular sample respondents were offered a post-paid cash reimbursement for their participation.

Weighting is generally used in survey analysis to compensate for sample designs and patterns of non-response that might bias results. A two-stage weighting procedure was used to weight these dual-frame samples. A first-stage weight of 0.5 was applied to all dual-users to account for the fact that they were included in both sample frames. All other cases were given a first-stage weight of 1. The second stage of weighting balanced sample demographics to population parameters. The sample was balanced – by form – to match national population parameters for sex, age, education, race, Hispanic origin, region (U.S. Census definitions), population d
ensity, and telephone usage. The White, non-Hispanic subgroup was also balanced on age, education and region. The basic weighting parameters came from a special analysis of the Census Bureau’s 2006 Annual Social and Economic Supplement (ASEC) that included all households in the continental United States that had a telephone. Based on an extrapolation from the National Health Interview Survey, the cell phone usage parameters were: cell-only = 14%, cell + landline = 60%, landline only = 26%.

The following table shows the error attributable to sampling that would be expected at the 95% level of confidence for different groups in the surveys:

Group Sample Size Plus or minusÂ……
October survey (total) 2,007 2.5 percentage points
Landline respondents 1,507 3.0 percentage points
Cell phone respondents 500 5.0 percentage points
Cell-only respondents 199 8.0 percentage points

December survey (total) 1,430 3.0 percentage points
Landline respondents 1,089 3.5 percentage points
Cell phone respondents 341 6.0 percentage points
Cell-only respondents 113 10.5 percentage points

In addition to sampling error, one should bear in mind that question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls.