Country: United States
Survey Organization: Social Science Research Solutions
Field Dates: May 12, 2009 through July 2, 2009
Sample: A nationally representative sample of 2,002 young adults ages 19 to 29
Interview Method: Telephone. Since many young adults use cell phones "mostly" or "exclusively," this survey employed a dual-frame landline and cell phone telephone design in which half (1,002) of the interviews were conducted by cell phone. The 25-minute telephone interviews were completed in both English and Spanish, according to the preference of the respondent.
Complete Methodology
Data come from the Commonwealth Fund Survey of Young Adults (2009), a national telephone survey conducted May 12, 2009 through July 2, 2009, among a nationally representative sample of 2,002 young adults ages 19 to 29 and living in the continental United States. The survey was conducted by Social Science Research Solutions (SSRS). Since many young adults use cell phones “mostly” or “exclusively,” this survey employed a dual-frame landline and cell phone telephone design in which half (1,002) of the interviews were conducted by cell phone. The 25-minute telephone interviews were completed in both English and Spanish, according to the preference of the respondent.
The landline portion of the sample used a disproportionate, stratified random digit dialing design to increase the potential of reaching young adult households overall, as well as those specifically low-income and African American and Hispanic. A prescreened strata was included, which supplemented the sample with additional interviews of households identified as having a 19-to-29-year-old in prior waves of SSRS’s national omnibus survey. The cell phone portion of the sample was accomplished using basic random digit dialing methodology of working cell phone exchanges. Using this dual-frame stratified sampling design, this study obtained an oversample of low-income, African American, and Hispanic adults. Survey data were weighted to 1) correct for the fact that not all survey respondents were selected with the same probability, and 2) account for gaps in coverage and nonresponse biases in the survey frame. In the first stage, SSRS developed design weights to compensate for sample-frame biases and the number of telephones in the household/cell phone-only status. Population counts for telephone status were requested from the National Center for Health Statistics and drawn from their National Health Insurance Survey. In the second stage, the data were weighted by age, education, geographic region, gender, and race/ethnicity using the 2007 American Community Survey population Exhibits. The resulting weighted sample is representative of the approximately 46 million adults ages 19 to 29.
The survey achieved a 32 percent response rate (calculated according to the standards of the American Association for Public Opinion Research). The survey has an overall margin of sampling error of +/– 2 percent at the 95 percent confidence level.